alexgenovese
/
sdxl-custom-model
Custom improvements like a custom callback to enhance the inference | It's a WIP and it may causes some wrong outputs
- Public
- 1.3K runs
-
A100 (80GB)
Prediction
alexgenovese/sdxl-custom-model:ecde520aIDoi4zbwdbq6utlohl52wpxotrxiStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day
- refiner
- true
- denoising
- 0.8
- seed_number
- 12345
- guidance_scale
- 15
- num_inference_steps
- 35
{ "width": 1024, "height": 1024, "prompt": "A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 15, "num_inference_steps": 35 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day", guidance_scale: 15, num_inference_steps: 35 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day", "guidance_scale": 15, "num_inference_steps": 35 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day", "guidance_scale": 15, "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day"' \ -i 'guidance_scale=15' \ -i 'num_inference_steps=35'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day", "guidance_scale": 15, "num_inference_steps": 35 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-18T08:29:55.627969Z", "created_at": "2023-11-18T08:25:42.305871Z", "data_removed": false, "error": null, "id": "oi4zbwdbq6utlohl52wpxotrxi", "input": { "width": 1024, "height": 1024, "prompt": "A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 15, "num_inference_steps": 35 }, "logs": "Starting fp16 torch.float32 cuda\nFused all loras in UNet\nApplied correction to prompts positive A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, nice bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts ,, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 946 max: 4.08 min: -4.43 mean: 0.04\n 0%| | 0/28 [00:00<?, ?it/s]\ntimestep: 919 max: 4.07 min: -4.43 mean: -0.03\n 4%|▎ | 1/28 [00:02<01:02, 2.32s/it]\ntimestep: 892 max: 4.23 min: -4.64 mean: 0.06\n 7%|▋ | 2/28 [00:03<00:38, 1.48s/it]\ntimestep: 865 max: 4.15 min: -4.49 mean: -0.0\n 11%|█ | 3/28 [00:04<00:33, 1.32s/it]\ntimestep: 838 max: 4.27 min: -4.57 mean: 0.04\n 14%|█▍ | 4/28 [00:05<00:27, 1.15s/it]\ntimestep: 811 max: 4.26 min: -4.62 mean: 0.01\n 18%|█▊ | 5/28 [00:06<00:24, 1.06s/it]\ntimestep: 784 max: 4.3 min: -4.57 mean: 0.03\n 21%|██▏ | 6/28 [00:07<00:22, 1.01s/it]\ntimestep: 757 max: 4.26 min: -4.7 mean: 0.02\n 25%|██▌ | 7/28 [00:07<00:20, 1.03it/s]\ntimestep: 730 max: 4.39 min: -4.69 mean:0.02\n 29%|██▊ | 8/28 [00:08<00:18, 1.05it/s]\ntimestep: 703 max: 4.24 min: -4.71 mean: 0.02\n 32%|███▏ | 9/28 [00:09<00:17, 1.07it/s]\ntimestep: 676 max: 4.22 min: -4.75 mean: 0.02\n 36%|███▌ | 10/28 [00:10<00:16, 1.09it/s]\ntimestep: 649 max: 4.17 min: -4.74 mean: 0.01\n 39%|███▉ | 11/28 [00:11<00:15, 1.10it/s]\ntimestep: 622 max: 4.1 min: -4.77 mean: 0.01\n 43%|████▎ | 12/28 [00:12<00:14, 1.10it/s]\ntimestep: 595 max: 4.1 min: -4.74 mean: 0.01\n 46%|████▋ | 13/28 [00:13<00:13, 1.11it/s]\ntimestep: 568 max: 4.08 min: -4.77 mean:0.01\n 50%|█████ | 14/28 [00:14<00:12, 1.11it/s]\ntimestep: 541 max: 4.12 min: -4.75 mean: 0.01\n 54%|█████▎ | 15/28 [00:15<00:11, 1.12it/s]\ntimestep: 514 max: 4.16 min: -4.76 mean: 0.02\n 57%|█████▋ | 16/28 [00:15<00:10, 1.12it/s]\ntimestep: 487 max: 4.16 min: -4.75 mean:0.02\n 61%|██████ | 17/28 [00:16<00:09, 1.12it/s]\ntimestep: 460 max: 4.18 min: -4.73 mean: 0.02\n 64%|██████▍ | 18/28 [00:17<00:08, 1.12it/s]\ntimestep: 433 max: 4.21 min: -4.71 mean: 0.02\n 68%|██████▊ | 19/28 [00:18<00:08, 1.12it/s]\ntimestep: 406 max: 4.2 min: -4.68 mean: 0.03\n 71%|███████▏ | 20/28 [00:19<00:07, 1.12it/s]\ntimestep: 379 max: 4.22min: -4.66 mean: 0.03\n 75%|███████▌ | 21/28 [00:20<00:06, 1.12it/s]\ntimestep: 352 max: 4.21 min: -4.62 mean: 0.04\n 79%|███████▊ | 22/28 [00:21<00:05, 1.12it/s]\ntimestep: 325 max: 4.21 min: -4.57 mean: 0.04\n 82%|████████▏ | 23/28 [00:22<00:04, 1.12it/s]\ntimestep: 298 max: 4.2 min:-4.5 mean: 0.04\n 86%|████████▌ | 24/28 [00:23<00:03, 1.12it/s]\ntimestep: 271 max: 4.19 min: -4.41 mean: 0.05\n 89%|████████▉ | 25/28 [00:24<00:02, 1.12it/s]\ntimestep: 244 max: 4.15 min: -4.29 mean: 0.05\n 93%|█████████▎| 26/28 [00:24<00:01, 1.12it/s]\ntimestep: 217 max: 4.11 min: -4.17 mean: 0.06\n 96%|█████████▋| 27/28 [00:25<00:00, 1.12it/s]\n100%|██████████| 28/28 [00:26<00:00, 1.12it/s]\n100%|██████████| 28/28 [00:26<00:00, 1.05it/s]\ntimestep: 197 max: 3.93 min: -3.92 mean: 0.05\n 0%| | 0/8 [00:00<?, ?it/s]\ntimestep: 169 max: 3.75 min: -3.67 mean: 0.05\n 12%|█▎ | 1/8 [00:00<00:05, 1.24it/s]\ntimestep: 141 max: 3.58 min: -3.42mean: 0.05\n 25%|██▌ | 2/8 [00:01<00:04, 1.24it/s]\ntimestep: 113 max: 3.4 min: -3.18 mean: 0.05\n 38%|███▊ | 3/8 [00:02<00:04, 1.24it/s]\ntimestep: 85 max: 3.25 min: -3.02 mean: 0.05\n 50%|█████ | 4/8 [00:03<00:03, 1.24it/s]\ntimestep: 57 max: 3.17 min: -2.9 mean: 0.05\n 62%|██████▎ | 5/8 [00:04<00:02, 1.24it/s]\ntimestep: 29 max: 3.05 min: -2.82 mean: 0.05\n 75%|███████▌ | 6/8 [00:04<00:01, 1.24it/s]\ntimestep: 1 max: 3.02 min: -2.84 mean: 0.05\n 88%|████████▊ | 7/8 [00:05<00:00, 1.24it/s]\n100%|██████████| 8/8 [00:06<00:00, 1.24it/s]\n100%|██████████| 8/8 [00:06<00:00, 1.24it/s]\nInference took: 36.194456338882446 17376", "metrics": { "predict_time": 37.431303, "total_time": 253.322098 }, "output": "https://replicate.delivery/pbxt/QFvqWhByrJ6zN5Snjv9fe9QpvpKvHDMCmcGUXn2CWneFAFzjA/image-17376-35.64189672470093.png", "started_at": "2023-11-18T08:29:18.196666Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/oi4zbwdbq6utlohl52wpxotrxi", "cancel": "https://api.replicate.com/v1/predictions/oi4zbwdbq6utlohl52wpxotrxi/cancel" }, "version": "b2dd68b5b5828f2a21cc922f64136dababe496214f4d27c7ac34136f05ef59f5" }Generated inStarting fp16 torch.float32 cuda Fused all loras in UNet Applied correction to prompts positive A woman walking in madison square garden, watching the viewer, dressed in blue jeans and white t-shirt, ultra realistic, realistic, 8k, sunny day, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, nice bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts ,, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 946 max: 4.08 min: -4.43 mean: 0.04 0%| | 0/28 [00:00<?, ?it/s] timestep: 919 max: 4.07 min: -4.43 mean: -0.03 4%|▎ | 1/28 [00:02<01:02, 2.32s/it] timestep: 892 max: 4.23 min: -4.64 mean: 0.06 7%|▋ | 2/28 [00:03<00:38, 1.48s/it] timestep: 865 max: 4.15 min: -4.49 mean: -0.0 11%|█ | 3/28 [00:04<00:33, 1.32s/it] timestep: 838 max: 4.27 min: -4.57 mean: 0.04 14%|█▍ | 4/28 [00:05<00:27, 1.15s/it] timestep: 811 max: 4.26 min: -4.62 mean: 0.01 18%|█▊ | 5/28 [00:06<00:24, 1.06s/it] timestep: 784 max: 4.3 min: -4.57 mean: 0.03 21%|██▏ | 6/28 [00:07<00:22, 1.01s/it] timestep: 757 max: 4.26 min: -4.7 mean: 0.02 25%|██▌ | 7/28 [00:07<00:20, 1.03it/s] timestep: 730 max: 4.39 min: -4.69 mean:0.02 29%|██▊ | 8/28 [00:08<00:18, 1.05it/s] timestep: 703 max: 4.24 min: -4.71 mean: 0.02 32%|███▏ | 9/28 [00:09<00:17, 1.07it/s] timestep: 676 max: 4.22 min: -4.75 mean: 0.02 36%|███▌ | 10/28 [00:10<00:16, 1.09it/s] timestep: 649 max: 4.17 min: -4.74 mean: 0.01 39%|███▉ | 11/28 [00:11<00:15, 1.10it/s] timestep: 622 max: 4.1 min: -4.77 mean: 0.01 43%|████▎ | 12/28 [00:12<00:14, 1.10it/s] timestep: 595 max: 4.1 min: -4.74 mean: 0.01 46%|████▋ | 13/28 [00:13<00:13, 1.11it/s] timestep: 568 max: 4.08 min: -4.77 mean:0.01 50%|█████ | 14/28 [00:14<00:12, 1.11it/s] timestep: 541 max: 4.12 min: -4.75 mean: 0.01 54%|█████▎ | 15/28 [00:15<00:11, 1.12it/s] timestep: 514 max: 4.16 min: -4.76 mean: 0.02 57%|█████▋ | 16/28 [00:15<00:10, 1.12it/s] timestep: 487 max: 4.16 min: -4.75 mean:0.02 61%|██████ | 17/28 [00:16<00:09, 1.12it/s] timestep: 460 max: 4.18 min: -4.73 mean: 0.02 64%|██████▍ | 18/28 [00:17<00:08, 1.12it/s] timestep: 433 max: 4.21 min: -4.71 mean: 0.02 68%|██████▊ | 19/28 [00:18<00:08, 1.12it/s] timestep: 406 max: 4.2 min: -4.68 mean: 0.03 71%|███████▏ | 20/28 [00:19<00:07, 1.12it/s] timestep: 379 max: 4.22min: -4.66 mean: 0.03 75%|███████▌ | 21/28 [00:20<00:06, 1.12it/s] timestep: 352 max: 4.21 min: -4.62 mean: 0.04 79%|███████▊ | 22/28 [00:21<00:05, 1.12it/s] timestep: 325 max: 4.21 min: -4.57 mean: 0.04 82%|████████▏ | 23/28 [00:22<00:04, 1.12it/s] timestep: 298 max: 4.2 min:-4.5 mean: 0.04 86%|████████▌ | 24/28 [00:23<00:03, 1.12it/s] timestep: 271 max: 4.19 min: -4.41 mean: 0.05 89%|████████▉ | 25/28 [00:24<00:02, 1.12it/s] timestep: 244 max: 4.15 min: -4.29 mean: 0.05 93%|█████████▎| 26/28 [00:24<00:01, 1.12it/s] timestep: 217 max: 4.11 min: -4.17 mean: 0.06 96%|█████████▋| 27/28 [00:25<00:00, 1.12it/s] 100%|██████████| 28/28 [00:26<00:00, 1.12it/s] 100%|██████████| 28/28 [00:26<00:00, 1.05it/s] timestep: 197 max: 3.93 min: -3.92 mean: 0.05 0%| | 0/8 [00:00<?, ?it/s] timestep: 169 max: 3.75 min: -3.67 mean: 0.05 12%|█▎ | 1/8 [00:00<00:05, 1.24it/s] timestep: 141 max: 3.58 min: -3.42mean: 0.05 25%|██▌ | 2/8 [00:01<00:04, 1.24it/s] timestep: 113 max: 3.4 min: -3.18 mean: 0.05 38%|███▊ | 3/8 [00:02<00:04, 1.24it/s] timestep: 85 max: 3.25 min: -3.02 mean: 0.05 50%|█████ | 4/8 [00:03<00:03, 1.24it/s] timestep: 57 max: 3.17 min: -2.9 mean: 0.05 62%|██████▎ | 5/8 [00:04<00:02, 1.24it/s] timestep: 29 max: 3.05 min: -2.82 mean: 0.05 75%|███████▌ | 6/8 [00:04<00:01, 1.24it/s] timestep: 1 max: 3.02 min: -2.84 mean: 0.05 88%|████████▊ | 7/8 [00:05<00:00, 1.24it/s] 100%|██████████| 8/8 [00:06<00:00, 1.24it/s] 100%|██████████| 8/8 [00:06<00:00, 1.24it/s] Inference took: 36.194456338882446 17376Prediction
alexgenovese/sdxl-custom-model:ecde520aIDgn3vlgjbix6umt7gzzncqizo6aStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt
- refiner
- true
- denoising
- 0.8
- seed_number
- 2222
- guidance_scale
- 15
- negative_prompt
- drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt", "refiner": true, "denoising": 0.8, "seed_number": 2222, "guidance_scale": 15, "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "num_inference_steps": 50 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt", guidance_scale: 15, negative_prompt: "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", num_inference_steps: 50 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt", "guidance_scale": 15, "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt", "guidance_scale": 15, "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt"' \ -i 'guidance_scale=15' \ -i 'negative_prompt="drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth"' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt", "guidance_scale": 15, "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-18T12:58:22.297569Z", "created_at": "2023-11-18T12:57:40.817775Z", "data_removed": false, "error": null, "id": "gn3vlgjbix6umt7gzzncqizo6a", "input": { "width": 1024, "height": 1024, "prompt": "a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt", "refiner": true, "denoising": 0.8, "seed_number": 2222, "guidance_scale": 15, "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "num_inference_steps": 50 }, "logs": "Starting fp16 torch.float32 cuda\nFused all loras in UNet\nApplied correction to prompts positive a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, nice bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch)1.10, open mouth ,, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 951 max: 4.2 min: -4.05 mean: 0.01\n 0%| | 0/40 [00:00<?, ?it/s]\ntimestep: 932 max: 4.2 min: -4.02 mean: 0.01\n 2%|▎ | 1/40 [00:00<00:30, 1.30it/s]\ntimestep: 913 max: 4.18 min: -4.09 mean: 0.04\n 5%|▌ | 2/40 [00:01<00:29, 1.30it/s]\ntimestep: 894 max: 4.17 min: -4.11 mean: 0.03\n 8%|▊ | 3/40 [00:02<00:28, 1.30it/s]\ntimestep: 875 max: 4.19 min: -4.15 mean:0.05\n 10%|█ | 4/40 [00:03<00:27, 1.30it/s]\ntimestep: 856 max: 4.13 min: -4.15 mean: 0.05\n 12%|█▎ | 5/40 [00:03<00:26, 1.30it/s]\ntimestep: 837 max: 4.18 min: -4.24 mean: 0.05\n 15%|█▌ | 6/40 [00:04<00:26, 1.30it/s]\ntimestep: 818 max: 4.15 min: -4.23 mean: 0.05\n 18%|█▊ | 7/40 [00:05<00:25, 1.30it/s]\ntimestep: 799 max: 4.18 min: -4.28 mean: 0.06\n 20%|██ | 8/40 [00:06<00:24, 1.30it/s]\ntimestep: 780 max: 4.17 min: -4.31 mean: 0.04\n 22%|██▎ | 9/40 [00:06<00:23, 1.30it/s]\ntimestep: 761 max: 4.2 min: -4.33 mean: 0.05\n 25%|██▌ | 10/40 [00:07<00:23, 1.30it/s]\ntimestep: 742 max: 4.2 min: -4.39 mean: 0.04\n 28%|██▊ | 11/40 [00:08<00:22, 1.30it/s]\ntimestep: 723 max: 4.23 min: -4.41 mean: 0.05\n 30%|███ | 12/40 [00:09<00:21, 1.30it/s]\ntimestep: 704 max: 4.25 min: -4.45 mean: 0.04\n 32%|███▎ | 13/40 [00:10<00:20, 1.30it/s]\ntimestep: 685 max: 4.27 min: -4.48 mean: 0.05\n 35%|███▌ | 14/40 [00:10<00:20, 1.30it/s]\ntimestep: 666 max: 4.29 min: -4.52 mean: 0.05\n 38%|███▊ | 15/40 [00:11<00:19, 1.30it/s]\ntimestep: 647 max: 4.3 min: -4.54 mean: 0.05\n 40%|████ | 16/40 [00:12<00:18, 1.30it/s]\ntimestep: 628 max: 4.31 min: -4.56 mean: 0.05\n 42%|████▎ | 17/40 [00:13<00:17, 1.30it/s]\ntimestep: 609 max: 4.32 min: -4.58 mean: 0.05\n 45%|████▌ | 18/40 [00:13<00:16, 1.30it/s]\ntimestep: 590 max: 4.32 min: -4.59 mean: 0.06\n 48%|████▊ | 19/40 [00:14<00:16, 1.30it/s]\ntimestep: 571 max: 4.31 min: -4.61 mean: 0.06\n 50%|█████ | 20/40 [00:15<00:15, 1.30it/s]\ntimestep: 552 max: 4.3 min: -4.62 mean: 0.06\n 52%|█████▎ | 21/40 [00:16<00:14, 1.29it/s]\ntimestep: 533 max: 4.28 min: -4.62 mean: 0.07\n 55%|█████▌ | 22/40 [00:16<00:13, 1.30it/s]\ntimestep: 514 max: 4.26 min: -4.63 mean: 0.07\n 57%|█████▊ | 23/40 [00:17<00:13, 1.30it/s]\ntimestep: 495 max: 4.25 min: -4.63 mean: 0.08\n 60%|██████ | 24/40 [00:18<00:12, 1.30it/s]\ntimestep: 476 max: 4.23 min: -4.63 mean: 0.08\n 62%|██████▎ | 25/40 [00:19<00:11, 1.30it/s]\ntimestep: 457 max: 4.21 min: -4.62mean: 0.09\n 65%|██████▌ | 26/40 [00:20<00:10, 1.30it/s]\ntimestep: 438 max: 4.2 min: -4.61 mean: 0.1\n 68%|██████▊ | 27/40 [00:20<00:10, 1.30it/s]\ntimestep: 419 max: 4.19 min: -4.6 mean: 0.1\n 70%|███████ | 28/40 [00:21<00:09, 1.30it/s]\ntimestep: 400 max: 4.16 min: -4.59 mean: 0.11\n 72%|███████▎ | 29/40 [00:22<00:08, 1.30it/s]\ntimestep: 381 max: 4.14 min: -4.57mean: 0.12\n 75%|███████▌ | 30/40 [00:23<00:07, 1.30it/s]\ntimestep: 362 max: 4.1 min: -4.54 mean: 0.12\n 78%|███████▊ | 31/40 [00:23<00:06, 1.30it/s]\ntimestep: 343 max: 4.07 min: -4.51 mean:0.13\n 80%|████████ | 32/40 [00:24<00:06, 1.30it/s]\ntimestep: 324 max: 4.03 min: -4.48 mean: 0.13\n 82%|████████▎ | 33/40 [00:25<00:05, 1.30it/s]\ntimestep: 305 max: 4.01 min: -4.44 mean:0.14\n 85%|████████▌ | 34/40 [00:26<00:04, 1.30it/s]\ntimestep: 286 max: 4.0 min: -4.39 mean: 0.15\n 88%|████████▊ | 35/40 [00:26<00:03, 1.30it/s]\ntimestep: 267 max: 4.0 min: -4.35 mean: 0.15\n 90%|█████████ | 36/40 [00:27<00:03, 1.30it/s]\ntimestep: 248 max: 4.01 min: -4.29 mean: 0.16\n 92%|█████████▎| 37/40 [00:28<00:02, 1.30it/s]\ntimestep: 229 max: 4.02 min: -4.24 mean: 0.16\n 95%|█████████▌| 38/40 [00:29<00:01, 1.30it/s]\ntimestep: 210 max: 4.02 min: -4.17 mean: 0.17\n 98%|█████████▊| 39/40 [00:30<00:00, 1.30it/s]\n100%|██████████| 40/40 [00:30<00:00, 1.30it/s]\n100%|██████████| 40/40 [00:30<00:00, 1.30it/s]\ntimestep: 181 max: 3.91 min: -4.01 mean: 0.17\n 0%| | 0/10 [00:00<?, ?it/s]\ntimestep: 161 max: 3.79 min: -3.85 mean: 0.17\n 10%|█ | 1/10 [00:00<00:05, 1.59it/s]\ntimestep: 141 max: 3.68 min: -3.69 mean: 0.17\n 20%|██ | 2/10 [00:01<00:05, 1.59it/s]\ntimestep: 121 max: 3.57 min: -3.53mean: 0.17\n 30%|███ | 3/10 [00:01<00:04, 1.59it/s]\ntimestep: 101 max: 3.46 min: -3.37mean: 0.17\n 40%|████ | 4/10 [00:02<00:03, 1.59it/s]\ntimestep: 81 max: 3.34 min: -3.27 mean: 0.17\n 50%|█████ | 5/10 [00:03<00:03, 1.59it/s]\ntimestep: 61 max: 3.21 min: -3.17 mean: 0.17\n 60%|██████ | 6/10 [00:03<00:02, 1.59it/s]\ntimestep: 41 max: 3.11 min: -3.09 mean: 0.17\n 70%|███████ | 7/10 [00:04<00:01, 1.59it/s]\ntimestep: 21 max: 3.07 min: -2.99 mean: 0.17\n 80%|████████ | 8/10 [00:05<00:01, 1.59it/s]\ntimestep: 1 max: 3.07 min: -2.98 mean: 0.17\n 90%|█████████ | 9/10 [00:05<00:00, 1.59it/s]\n100%|██████████| 10/10 [00:06<00:00, 1.59it/s]\n100%|██████████| 10/10 [00:06<00:00, 1.59it/s]\nInference took: 40.658628940582275 40085", "metrics": { "predict_time": 41.463529, "total_time": 41.479794 }, "output": "https://replicate.delivery/pbxt/ZNhAJv10fg1fLk8unYrVz4csySRG2wX6LQWP6gjlQVAtbm5RA/image-40085-39.909873723983765.png", "started_at": "2023-11-18T12:57:40.834040Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/gn3vlgjbix6umt7gzzncqizo6a", "cancel": "https://api.replicate.com/v1/predictions/gn3vlgjbix6umt7gzzncqizo6a/cancel" }, "version": "b2dd68b5b5828f2a21cc922f64136dababe496214f4d27c7ac34136f05ef59f5" }Generated inStarting fp16 torch.float32 cuda Fused all loras in UNet Applied correction to prompts positive a woman is walking in Madison Square Garden, sunny day, blue jeans and white t-shirt, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, nice bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly, 3d render, afro, (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch)1.10, open mouth ,, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 951 max: 4.2 min: -4.05 mean: 0.01 0%| | 0/40 [00:00<?, ?it/s] timestep: 932 max: 4.2 min: -4.02 mean: 0.01 2%|▎ | 1/40 [00:00<00:30, 1.30it/s] timestep: 913 max: 4.18 min: -4.09 mean: 0.04 5%|▌ | 2/40 [00:01<00:29, 1.30it/s] timestep: 894 max: 4.17 min: -4.11 mean: 0.03 8%|▊ | 3/40 [00:02<00:28, 1.30it/s] timestep: 875 max: 4.19 min: -4.15 mean:0.05 10%|█ | 4/40 [00:03<00:27, 1.30it/s] timestep: 856 max: 4.13 min: -4.15 mean: 0.05 12%|█▎ | 5/40 [00:03<00:26, 1.30it/s] timestep: 837 max: 4.18 min: -4.24 mean: 0.05 15%|█▌ | 6/40 [00:04<00:26, 1.30it/s] timestep: 818 max: 4.15 min: -4.23 mean: 0.05 18%|█▊ | 7/40 [00:05<00:25, 1.30it/s] timestep: 799 max: 4.18 min: -4.28 mean: 0.06 20%|██ | 8/40 [00:06<00:24, 1.30it/s] timestep: 780 max: 4.17 min: -4.31 mean: 0.04 22%|██▎ | 9/40 [00:06<00:23, 1.30it/s] timestep: 761 max: 4.2 min: -4.33 mean: 0.05 25%|██▌ | 10/40 [00:07<00:23, 1.30it/s] timestep: 742 max: 4.2 min: -4.39 mean: 0.04 28%|██▊ | 11/40 [00:08<00:22, 1.30it/s] timestep: 723 max: 4.23 min: -4.41 mean: 0.05 30%|███ | 12/40 [00:09<00:21, 1.30it/s] timestep: 704 max: 4.25 min: -4.45 mean: 0.04 32%|███▎ | 13/40 [00:10<00:20, 1.30it/s] timestep: 685 max: 4.27 min: -4.48 mean: 0.05 35%|███▌ | 14/40 [00:10<00:20, 1.30it/s] timestep: 666 max: 4.29 min: -4.52 mean: 0.05 38%|███▊ | 15/40 [00:11<00:19, 1.30it/s] timestep: 647 max: 4.3 min: -4.54 mean: 0.05 40%|████ | 16/40 [00:12<00:18, 1.30it/s] timestep: 628 max: 4.31 min: -4.56 mean: 0.05 42%|████▎ | 17/40 [00:13<00:17, 1.30it/s] timestep: 609 max: 4.32 min: -4.58 mean: 0.05 45%|████▌ | 18/40 [00:13<00:16, 1.30it/s] timestep: 590 max: 4.32 min: -4.59 mean: 0.06 48%|████▊ | 19/40 [00:14<00:16, 1.30it/s] timestep: 571 max: 4.31 min: -4.61 mean: 0.06 50%|█████ | 20/40 [00:15<00:15, 1.30it/s] timestep: 552 max: 4.3 min: -4.62 mean: 0.06 52%|█████▎ | 21/40 [00:16<00:14, 1.29it/s] timestep: 533 max: 4.28 min: -4.62 mean: 0.07 55%|█████▌ | 22/40 [00:16<00:13, 1.30it/s] timestep: 514 max: 4.26 min: -4.63 mean: 0.07 57%|█████▊ | 23/40 [00:17<00:13, 1.30it/s] timestep: 495 max: 4.25 min: -4.63 mean: 0.08 60%|██████ | 24/40 [00:18<00:12, 1.30it/s] timestep: 476 max: 4.23 min: -4.63 mean: 0.08 62%|██████▎ | 25/40 [00:19<00:11, 1.30it/s] timestep: 457 max: 4.21 min: -4.62mean: 0.09 65%|██████▌ | 26/40 [00:20<00:10, 1.30it/s] timestep: 438 max: 4.2 min: -4.61 mean: 0.1 68%|██████▊ | 27/40 [00:20<00:10, 1.30it/s] timestep: 419 max: 4.19 min: -4.6 mean: 0.1 70%|███████ | 28/40 [00:21<00:09, 1.30it/s] timestep: 400 max: 4.16 min: -4.59 mean: 0.11 72%|███████▎ | 29/40 [00:22<00:08, 1.30it/s] timestep: 381 max: 4.14 min: -4.57mean: 0.12 75%|███████▌ | 30/40 [00:23<00:07, 1.30it/s] timestep: 362 max: 4.1 min: -4.54 mean: 0.12 78%|███████▊ | 31/40 [00:23<00:06, 1.30it/s] timestep: 343 max: 4.07 min: -4.51 mean:0.13 80%|████████ | 32/40 [00:24<00:06, 1.30it/s] timestep: 324 max: 4.03 min: -4.48 mean: 0.13 82%|████████▎ | 33/40 [00:25<00:05, 1.30it/s] timestep: 305 max: 4.01 min: -4.44 mean:0.14 85%|████████▌ | 34/40 [00:26<00:04, 1.30it/s] timestep: 286 max: 4.0 min: -4.39 mean: 0.15 88%|████████▊ | 35/40 [00:26<00:03, 1.30it/s] timestep: 267 max: 4.0 min: -4.35 mean: 0.15 90%|█████████ | 36/40 [00:27<00:03, 1.30it/s] timestep: 248 max: 4.01 min: -4.29 mean: 0.16 92%|█████████▎| 37/40 [00:28<00:02, 1.30it/s] timestep: 229 max: 4.02 min: -4.24 mean: 0.16 95%|█████████▌| 38/40 [00:29<00:01, 1.30it/s] timestep: 210 max: 4.02 min: -4.17 mean: 0.17 98%|█████████▊| 39/40 [00:30<00:00, 1.30it/s] 100%|██████████| 40/40 [00:30<00:00, 1.30it/s] 100%|██████████| 40/40 [00:30<00:00, 1.30it/s] timestep: 181 max: 3.91 min: -4.01 mean: 0.17 0%| | 0/10 [00:00<?, ?it/s] timestep: 161 max: 3.79 min: -3.85 mean: 0.17 10%|█ | 1/10 [00:00<00:05, 1.59it/s] timestep: 141 max: 3.68 min: -3.69 mean: 0.17 20%|██ | 2/10 [00:01<00:05, 1.59it/s] timestep: 121 max: 3.57 min: -3.53mean: 0.17 30%|███ | 3/10 [00:01<00:04, 1.59it/s] timestep: 101 max: 3.46 min: -3.37mean: 0.17 40%|████ | 4/10 [00:02<00:03, 1.59it/s] timestep: 81 max: 3.34 min: -3.27 mean: 0.17 50%|█████ | 5/10 [00:03<00:03, 1.59it/s] timestep: 61 max: 3.21 min: -3.17 mean: 0.17 60%|██████ | 6/10 [00:03<00:02, 1.59it/s] timestep: 41 max: 3.11 min: -3.09 mean: 0.17 70%|███████ | 7/10 [00:04<00:01, 1.59it/s] timestep: 21 max: 3.07 min: -2.99 mean: 0.17 80%|████████ | 8/10 [00:05<00:01, 1.59it/s] timestep: 1 max: 3.07 min: -2.98 mean: 0.17 90%|█████████ | 9/10 [00:05<00:00, 1.59it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] Inference took: 40.658628940582275 40085Prediction
alexgenovese/sdxl-custom-model:ecde520aIDb3pb7ndbun72kbscco2va666uaStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))
- refiner
- true
- denoising
- 0.8
- seed_number
- 12345
- guidance_scale
- 8
- num_inference_steps
- 35
{ "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 8, "num_inference_steps": 35 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", guidance_scale: 8, num_inference_steps: 35 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "guidance_scale": 8, "num_inference_steps": 35 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "guidance_scale": 8, "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))"' \ -i 'guidance_scale=8' \ -i 'num_inference_steps=35'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "guidance_scale": 8, "num_inference_steps": 35 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-19T12:17:51.933333Z", "created_at": "2023-11-19T12:15:56.219475Z", "data_removed": false, "error": null, "id": "b3pb7ndbun72kbscco2va666ua", "input": { "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 8, "num_inference_steps": 35 }, "logs": "Starting fp16 torch.float32 cuda\nFused all loras in UNet\nApplied correction to prompts positive a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, (full body)1.21, (3/4 view)1.21, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 946 max: 3.99 min: -4.34 mean: -0.01\n 0%| | 0/28 [00:00<?, ?it/s]\ntimestep: 919 max: 4.03 min: -4.43 mean: 0.0\n 4%|▎ | 1/28 [00:01<00:35, 1.30s/it]\ntimestep: 892 max: 4.04 min: -4.39 mean: -0.01\n 7%|▋ | 2/28 [00:02<00:25, 1.01it/s]\ntimestep: 865 max: 4.05 min: -4.46 mean: -0.01\n 11%|█ | 3/28 [00:02<00:23, 1.06it/s]\ntimestep: 838 max: 4.04 min: -4.48 mean: -0.02\n 14%|█▍ | 4/28 [00:03<00:20, 1.15it/s]\ntimestep: 811 max: 4.04 min: -4.51 mean: -0.02\n 18%|█▊ | 5/28 [00:04<00:19, 1.20it/s]\ntimestep: 784 max: 4.04 min: -4.53 mean: -0.02\n 21%|██▏ | 6/28 [00:05<00:17, 1.24it/s]\ntimestep: 757 max: 4.03 min: -4.55mean: -0.02\n 25%|██▌ | 7/28 [00:06<00:16, 1.26it/s]\ntimestep: 730 max: 4.03 min: -4.56 mean: -0.03\n 29%|██▊ | 8/28 [00:06<00:15, 1.27it/s]\ntimestep: 703 max: 4.0 min: -4.55 mean: -0.03\n 32%|███▏ | 9/28 [00:07<00:14, 1.28it/s]\ntimestep: 676 max: 3.97 min: -4.54 mean: -0.03\n 36%|███▌ | 10/28 [00:08<00:13, 1.29it/s]\ntimestep: 649 max: 3.96 min: -4.54 mean: -0.03\n 39%|███▉ | 11/28 [00:09<00:13, 1.29it/s]\ntimestep: 622 max: 3.94 min: -4.53 mean: -0.03\n 43%|████▎ | 12/28 [00:09<00:12, 1.30it/s]\ntimestep: 595 max: 3.91 min: -4.51 mean: -0.03\n 46%|████▋ | 13/28 [00:10<00:11, 1.30it/s]\ntimestep: 568 max: 3.88 min: -4.5 mean: -0.03\n 50%|█████ | 14/28 [00:11<00:10, 1.30it/s]\ntimestep: 541 max: 3.84 min: -4.48 mean: -0.03\n 54%|█████▎ | 15/28 [00:12<00:09, 1.30it/s]\ntimestep: 514 max: 3.8 min: -4.45 mean: -0.03\n 57%|█████▋ | 16/28 [00:12<00:09, 1.30it/s]\ntimestep: 487 max: 3.75 min: -4.42 mean: -0.03\n 61%|██████ | 17/28 [00:13<00:08, 1.30it/s]\ntimestep: 460 max: 3.7 min: -4.37 mean: -0.03\n 64%|██████▍ | 18/28 [00:14<00:07, 1.31it/s]\ntimestep: 433 max: 3.64 min: -4.32 mean: -0.03\n 68%|██████▊ | 19/28 [00:15<00:06, 1.31it/s]\ntimestep: 406 max: 3.57 min: -4.27 mean: -0.03\n 71%|███████▏ | 20/28 [00:15<00:06, 1.31it/s]\ntimestep: 379 max: 3.5 min: -4.2 mean: -0.03\n 75%|███████▌ | 21/28 [00:16<00:05, 1.31it/s]\ntimestep: 352 max: 3.43 min: -4.13 mean: -0.03\n 79%|███████▊ | 22/28 [00:17<00:04, 1.31it/s]\ntimestep: 325 max: 3.36 min: -4.05 mean: -0.03\n 82%|████████▏ | 23/28 [00:18<00:03, 1.31it/s]\ntimestep: 298 max: 3.3 min: -3.96 mean: -0.03\n 86%|████████▌ | 24/28 [00:19<00:03, 1.31it/s]\ntimestep: 271 max: 3.29 min: -3.87 mean: -0.03\n 89%|████████▉ | 25/28 [00:19<00:02, 1.31it/s]\ntimestep: 244 max: 3.27 min: -3.8mean: -0.02\n 93%|█████████▎| 26/28 [00:20<00:01, 1.31it/s]\ntimestep: 217 max: 3.26 min: -3.74 mean: -0.02\n 96%|█████████▋| 27/28 [00:21<00:00, 1.31it/s]\n100%|██████████| 28/28 [00:22<00:00, 1.31it/s]\n100%|██████████| 28/28 [00:22<00:00, 1.27it/s]\ntimestep: 197 max: 3.13 min: -3.54 mean: -0.02\n 0%| | 0/8 [00:00<?, ?it/s]\ntimestep: 169 max: 3.01 min: -3.35 mean: -0.02\n 12%|█▎ | 1/8 [00:00<00:04, 1.58it/s]\ntimestep: 141 max: 2.9 min: -3.17 mean: -0.02\n 25%|██▌ | 2/8 [00:01<00:03, 1.59it/s]\ntimestep: 113 max: 2.8 min: -2.98 mean: -0.02\n 38%|███▊ | 3/8 [00:01<00:03, 1.59it/s]\ntimestep: 85 max: 2.7 min: -2.79 mean: -0.03\n 50%|█████ | 4/8 [00:02<00:02, 1.59it/s]\ntimestep: 57 max: 2.58 min: -2.58 mean: -0.03\n 62%|██████▎ | 5/8 [00:03<00:01, 1.59it/s]\ntimestep: 29 max: 2.4 min: -2.42 mean: -0.03\n 75%|███████▌ | 6/8 [00:03<00:01, 1.59it/s]\ntimestep: 1 max: 2.45 min: -2.42 mean: -0.03\n 88%|████████▊ | 7/8 [00:04<00:00, 1.59it/s]\n100%|██████████| 8/8 [00:05<00:00, 1.59it/s]\n100%|██████████| 8/8 [00:05<00:00, 1.59it/s]\nInference took: 31.832138061523438 34902", "metrics": { "predict_time": 32.340615, "total_time": 115.713858 }, "output": "https://replicate.delivery/pbxt/QYKKQEkUZJLZCZ449kcbFJ3PWD56q4ht5zZJbqcHEfi3d98IA/image-34902-31.21769404411316.png", "started_at": "2023-11-19T12:17:19.592718Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/b3pb7ndbun72kbscco2va666ua", "cancel": "https://api.replicate.com/v1/predictions/b3pb7ndbun72kbscco2va666ua/cancel" }, "version": "a08504bd6b123bb993f648c6361041a3cc3f721a24ab6a1619b10f03dd8c0dff" }Generated inStarting fp16 torch.float32 cuda Fused all loras in UNet Applied correction to prompts positive a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, (full body)1.21, (3/4 view)1.21, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 946 max: 3.99 min: -4.34 mean: -0.01 0%| | 0/28 [00:00<?, ?it/s] timestep: 919 max: 4.03 min: -4.43 mean: 0.0 4%|▎ | 1/28 [00:01<00:35, 1.30s/it] timestep: 892 max: 4.04 min: -4.39 mean: -0.01 7%|▋ | 2/28 [00:02<00:25, 1.01it/s] timestep: 865 max: 4.05 min: -4.46 mean: -0.01 11%|█ | 3/28 [00:02<00:23, 1.06it/s] timestep: 838 max: 4.04 min: -4.48 mean: -0.02 14%|█▍ | 4/28 [00:03<00:20, 1.15it/s] timestep: 811 max: 4.04 min: -4.51 mean: -0.02 18%|█▊ | 5/28 [00:04<00:19, 1.20it/s] timestep: 784 max: 4.04 min: -4.53 mean: -0.02 21%|██▏ | 6/28 [00:05<00:17, 1.24it/s] timestep: 757 max: 4.03 min: -4.55mean: -0.02 25%|██▌ | 7/28 [00:06<00:16, 1.26it/s] timestep: 730 max: 4.03 min: -4.56 mean: -0.03 29%|██▊ | 8/28 [00:06<00:15, 1.27it/s] timestep: 703 max: 4.0 min: -4.55 mean: -0.03 32%|███▏ | 9/28 [00:07<00:14, 1.28it/s] timestep: 676 max: 3.97 min: -4.54 mean: -0.03 36%|███▌ | 10/28 [00:08<00:13, 1.29it/s] timestep: 649 max: 3.96 min: -4.54 mean: -0.03 39%|███▉ | 11/28 [00:09<00:13, 1.29it/s] timestep: 622 max: 3.94 min: -4.53 mean: -0.03 43%|████▎ | 12/28 [00:09<00:12, 1.30it/s] timestep: 595 max: 3.91 min: -4.51 mean: -0.03 46%|████▋ | 13/28 [00:10<00:11, 1.30it/s] timestep: 568 max: 3.88 min: -4.5 mean: -0.03 50%|█████ | 14/28 [00:11<00:10, 1.30it/s] timestep: 541 max: 3.84 min: -4.48 mean: -0.03 54%|█████▎ | 15/28 [00:12<00:09, 1.30it/s] timestep: 514 max: 3.8 min: -4.45 mean: -0.03 57%|█████▋ | 16/28 [00:12<00:09, 1.30it/s] timestep: 487 max: 3.75 min: -4.42 mean: -0.03 61%|██████ | 17/28 [00:13<00:08, 1.30it/s] timestep: 460 max: 3.7 min: -4.37 mean: -0.03 64%|██████▍ | 18/28 [00:14<00:07, 1.31it/s] timestep: 433 max: 3.64 min: -4.32 mean: -0.03 68%|██████▊ | 19/28 [00:15<00:06, 1.31it/s] timestep: 406 max: 3.57 min: -4.27 mean: -0.03 71%|███████▏ | 20/28 [00:15<00:06, 1.31it/s] timestep: 379 max: 3.5 min: -4.2 mean: -0.03 75%|███████▌ | 21/28 [00:16<00:05, 1.31it/s] timestep: 352 max: 3.43 min: -4.13 mean: -0.03 79%|███████▊ | 22/28 [00:17<00:04, 1.31it/s] timestep: 325 max: 3.36 min: -4.05 mean: -0.03 82%|████████▏ | 23/28 [00:18<00:03, 1.31it/s] timestep: 298 max: 3.3 min: -3.96 mean: -0.03 86%|████████▌ | 24/28 [00:19<00:03, 1.31it/s] timestep: 271 max: 3.29 min: -3.87 mean: -0.03 89%|████████▉ | 25/28 [00:19<00:02, 1.31it/s] timestep: 244 max: 3.27 min: -3.8mean: -0.02 93%|█████████▎| 26/28 [00:20<00:01, 1.31it/s] timestep: 217 max: 3.26 min: -3.74 mean: -0.02 96%|█████████▋| 27/28 [00:21<00:00, 1.31it/s] 100%|██████████| 28/28 [00:22<00:00, 1.31it/s] 100%|██████████| 28/28 [00:22<00:00, 1.27it/s] timestep: 197 max: 3.13 min: -3.54 mean: -0.02 0%| | 0/8 [00:00<?, ?it/s] timestep: 169 max: 3.01 min: -3.35 mean: -0.02 12%|█▎ | 1/8 [00:00<00:04, 1.58it/s] timestep: 141 max: 2.9 min: -3.17 mean: -0.02 25%|██▌ | 2/8 [00:01<00:03, 1.59it/s] timestep: 113 max: 2.8 min: -2.98 mean: -0.02 38%|███▊ | 3/8 [00:01<00:03, 1.59it/s] timestep: 85 max: 2.7 min: -2.79 mean: -0.03 50%|█████ | 4/8 [00:02<00:02, 1.59it/s] timestep: 57 max: 2.58 min: -2.58 mean: -0.03 62%|██████▎ | 5/8 [00:03<00:01, 1.59it/s] timestep: 29 max: 2.4 min: -2.42 mean: -0.03 75%|███████▌ | 6/8 [00:03<00:01, 1.59it/s] timestep: 1 max: 2.45 min: -2.42 mean: -0.03 88%|████████▊ | 7/8 [00:04<00:00, 1.59it/s] 100%|██████████| 8/8 [00:05<00:00, 1.59it/s] 100%|██████████| 8/8 [00:05<00:00, 1.59it/s] Inference took: 31.832138061523438 34902Prediction
alexgenovese/sdxl-custom-model:ecde520aIDylxihr3bxfgb32cdgnljb3mpqqStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, ((highly detailed high fashion black dress)), beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering
- refiner
- true
- denoising
- 0.8
- seed_number
- 12345
- guidance_scale
- 12
- negative_prompt
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, ((highly detailed high fashion black dress)), beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 12, "negative_prompt": "", "num_inference_steps": 50 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, ((highly detailed high fashion black dress)), beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering", guidance_scale: 12, negative_prompt: "", num_inference_steps: 50 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, ((highly detailed high fashion black dress)), beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering", "guidance_scale": 12, "negative_prompt": "", "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, ((highly detailed high fashion black dress)), beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering", "guidance_scale": 12, "negative_prompt": "", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, ((highly detailed high fashion black dress)), beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering"' \ -i 'guidance_scale=12' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, ((highly detailed high fashion black dress)), beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering", "guidance_scale": 12, "negative_prompt": "", "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-19T12:21:20.730161Z", "created_at": "2023-11-19T12:20:39.095064Z", "data_removed": false, "error": null, "id": "ylxihr3bxfgb32cdgnljb3mpqq", "input": { "width": 1024, "height": 1024, "prompt": "realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, ((highly detailed high fashion black dress)), beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 12, "negative_prompt": "", "num_inference_steps": 50 }, "logs": "Starting fp16 torch.float32 cuda\nThe current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported.\nFused all loras in UNet\nApplied correction to prompts positive realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, (highly detailed high fashion black dress)1.21, beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 951 max: 4.03 min: -4.32 mean: -0.03\n 0%| | 0/40 [00:00<?, ?it/s]\ntimestep: 932 max: 3.97 min: -4.33 mean: -0.0\n 2%|▎ | 1/40 [00:00<00:29, 1.31it/s]\ntimestep: 913 max: 4.01 min: -4.38mean: -0.04\n 5%|▌ | 2/40 [00:01<00:29, 1.31it/s]\ntimestep: 894 max: 4.01 min: -4.4 mean: -0.01\n 8%|▊ | 3/40 [00:02<00:28, 1.31it/s]\ntimestep: 875 max: 4.07 min: -4.41 mean: -0.05\n 10%|█ | 4/40 [00:03<00:27, 1.31it/s]\ntimestep: 856 max: 4.06 min: -4.45 mean: -0.03\n 12%|█▎ | 5/40 [00:03<00:26, 1.31it/s]\ntimestep: 837 max: 4.07 min: -4.44 mean: -0.05\n 15%|█▌ | 6/40 [00:04<00:25, 1.31it/s]\ntimestep: 818 max: 4.06 min: -4.47 mean: -0.04\n 18%|█▊ | 7/40 [00:05<00:25, 1.31it/s]\ntimestep: 799 max: 4.06 min: -4.47 mean: -0.05\n 20%|██ | 8/40 [00:06<00:24, 1.31it/s]\ntimestep: 780 max: 4.06 min: -4.48 mean:-0.05\n 22%|██▎ | 9/40 [00:06<00:23, 1.31it/s]\ntimestep: 761 max: 4.04 min: -4.48 mean: -0.06\n 25%|██▌ | 10/40 [00:07<00:22, 1.31it/s]\ntimestep: 742 max: 4.04 min: -4.49 mean: -0.07\n 28%|██▊ | 11/40 [00:08<00:22, 1.31it/s]\ntimestep: 723 max: 4.04 min: -4.49 mean: -0.07\n 30%|███ | 12/40 [00:09<00:21, 1.31it/s]\ntimestep: 704 max: 4.04 min: -4.5 mean: -0.08\n 32%|███▎ | 13/40 [00:09<00:20, 1.31it/s]\ntimestep: 685 max: 4.04 min: -4.5 mean: -0.08\n 35%|███▌ | 14/40 [00:10<00:19, 1.31it/s]\ntimestep: 666 max: 4.04 min: -4.5 mean: -0.09\n 38%|███▊ | 15/40 [00:11<00:19, 1.31it/s]\ntimestep: 647 max: 4.04 min: -4.5 mean: -0.1\n 40%|████ | 16/40 [00:12<00:18, 1.31it/s]\ntimestep: 628 max: 4.03 min: -4.5 mean: -0.1\n 42%|████▎ | 17/40 [00:13<00:17, 1.31it/s]\ntimestep: 609 max: 4.01 min: -4.49 mean: -0.11\n 45%|████▌ | 18/40 [00:13<00:16, 1.31it/s]\ntimestep: 590 max: 4.0 min: -4.48 mean: -0.11\n 48%|████▊ | 19/40 [00:14<00:16, 1.31it/s]\ntimestep: 571 max: 3.98 min: -4.47 mean: -0.12\n 50%|█████ | 20/40 [00:15<00:15, 1.31it/s]\ntimestep: 552 max: 3.95 min: -4.45 mean: -0.12\n 52%|█████▎ | 21/40 [00:16<00:14, 1.31it/s]\ntimestep: 533 max: 3.93 min: -4.43 mean: -0.13\n 55%|█████▌ | 22/40 [00:16<00:13, 1.31it/s]\ntimestep: 514 max: 3.9 min: -4.41 mean: -0.13\n 57%|█████▊ | 23/40 [00:17<00:13, 1.31it/s]\ntimestep: 495 max: 3.87 min: -4.38 mean: -0.14\n 60%|██████ | 24/40 [00:18<00:12, 1.31it/s]\ntimestep: 476 max: 3.83 min: -4.34 mean: -0.14\n 62%|██████▎ | 25/40 [00:19<00:11, 1.31it/s]\ntimestep: 457 max: 3.79 min: -4.31 mean: -0.14\n 65%|██████▌ | 26/40 [00:19<00:10, 1.31it/s]\ntimestep: 438 max: 3.74 min: -4.26 mean: -0.15\n 68%|██████▊ | 27/40 [00:20<00:09, 1.31it/s]\ntimestep: 419 max: 3.69 min: -4.21 mean: -0.15\n 70%|███████ | 28/40 [00:21<00:09, 1.31it/s]\ntimestep: 400 max: 3.63 min: -4.16 mean: -0.15\n 72%|███████▎ | 29/40 [00:22<00:08, 1.31it/s]\ntimestep: 381 max: 3.56 min: -4.1 mean: -0.16\n 75%|███████▌ | 30/40 [00:22<00:07, 1.31it/s]\ntimestep: 362 max: 3.54 min: -4.04 mean: -0.16\n 78%|███████▊ | 31/40 [00:23<00:06, 1.30it/s]\ntimestep: 343 max: 3.51 min: -3.98 mean: -0.16\n 80%|████████ | 32/40 [00:24<00:06, 1.31it/s]\ntimestep: 324 max: 3.48 min: -3.93 mean: -0.16\n 82%|████████▎ | 33/40 [00:25<00:05, 1.31it/s]\ntimestep: 305 max: 3.47 min: -3.89 mean: -0.17\n 85%|████████▌ | 34/40 [00:26<00:04, 1.31it/s]\ntimestep: 286 max: 3.46 min: -3.86 mean: -0.17\n 88%|████████▊ | 35/40 [00:26<00:03, 1.30it/s]\ntimestep: 267 max: 3.46 min: -3.81 mean: -0.17\n 90%|█████████ | 36/40 [00:27<00:03, 1.31it/s]\ntimestep: 248 max: 3.45 min: -3.77 mean: -0.17\n 92%|█████████▎| 37/40 [00:28<00:02, 1.31it/s]\ntimestep: 229 max: 3.44 min: -3.72 mean: -0.17\n 95%|█████████▌| 38/40 [00:29<00:01, 1.31it/s]\ntimestep: 210 max: 3.42 min: -3.66 mean: -0.17\n 98%|█████████▊| 39/40 [00:29<00:00, 1.31it/s]\n100%|██████████| 40/40 [00:30<00:00, 1.31it/s]\n100%|██████████| 40/40 [00:30<00:00, 1.31it/s]\ntimestep: 181 max: 3.3 min: -3.52 mean: -0.17\n 0%| | 0/10 [00:00<?, ?it/s]\ntimestep: 161 max: 3.21 min: -3.38 mean: -0.17\n 10%|█ | 1/10 [00:00<00:05, 1.59it/s]\ntimestep: 141 max: 3.17 min: -3.24 mean: -0.17\n 20%|██ | 2/10 [00:01<00:05, 1.59it/s]\ntimestep: 121 max: 3.13 min: -3.11 mean: -0.17\n 30%|███ | 3/10 [00:01<00:04, 1.59it/s]\ntimestep: 101 max: 3.09 min: -2.97 mean: -0.17\n 40%|████ | 4/10 [00:02<00:03, 1.59it/s]\ntimestep: 81 max: 3.04 min: -2.89 mean: -0.17\n 50%|█████ | 5/10 [00:03<00:03, 1.59it/s]\ntimestep: 61 max: 3.0 min: -2.82 mean: -0.17\n 60%|██████ | 6/10 [00:03<00:02, 1.59it/s]\ntimestep: 41 max: 2.95 min: -2.73 mean: -0.17\n 70%|███████ | 7/10 [00:04<00:01, 1.59it/s]\ntimestep: 21 max: 2.99 min: -2.61 mean: -0.17\n 80%|████████ | 8/10 [00:05<00:01, 1.59it/s]\ntimestep: 1 max: 3.02 min: -2.58 mean: -0.17\n 90%|█████████ | 9/10 [00:05<00:00, 1.59it/s]\n100%|██████████| 10/10 [00:06<00:00, 1.59it/s]\n100%|██████████| 10/10 [00:06<00:00, 1.59it/s]\nInference took: 41.25201749801636 12700", "metrics": { "predict_time": 41.606516, "total_time": 41.635097 }, "output": "https://replicate.delivery/pbxt/T9w2K6WPUA6fbitU9aIVxXPMqMeF7TuawHpCfaSAkfhD8rnHB/image-12700-40.60373544692993.png", "started_at": "2023-11-19T12:20:39.123645Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ylxihr3bxfgb32cdgnljb3mpqq", "cancel": "https://api.replicate.com/v1/predictions/ylxihr3bxfgb32cdgnljb3mpqq/cancel" }, "version": "a08504bd6b123bb993f648c6361041a3cc3f721a24ab6a1619b10f03dd8c0dff" }Generated inStarting fp16 torch.float32 cuda The current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported. Fused all loras in UNet Applied correction to prompts positive realistic dramatic action photo, female, runway model, 22yo, styled hair, majestic, elegant, (highly detailed high fashion black dress)1.21, beautiful, feminine, detailed face, detailed pupils, detailed skin texture, perfect makeup, majestic, at a high fashion gala, hyper realistic, cinematic lighting, absurdres, finely detailed, subsurface scattering, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 951 max: 4.03 min: -4.32 mean: -0.03 0%| | 0/40 [00:00<?, ?it/s] timestep: 932 max: 3.97 min: -4.33 mean: -0.0 2%|▎ | 1/40 [00:00<00:29, 1.31it/s] timestep: 913 max: 4.01 min: -4.38mean: -0.04 5%|▌ | 2/40 [00:01<00:29, 1.31it/s] timestep: 894 max: 4.01 min: -4.4 mean: -0.01 8%|▊ | 3/40 [00:02<00:28, 1.31it/s] timestep: 875 max: 4.07 min: -4.41 mean: -0.05 10%|█ | 4/40 [00:03<00:27, 1.31it/s] timestep: 856 max: 4.06 min: -4.45 mean: -0.03 12%|█▎ | 5/40 [00:03<00:26, 1.31it/s] timestep: 837 max: 4.07 min: -4.44 mean: -0.05 15%|█▌ | 6/40 [00:04<00:25, 1.31it/s] timestep: 818 max: 4.06 min: -4.47 mean: -0.04 18%|█▊ | 7/40 [00:05<00:25, 1.31it/s] timestep: 799 max: 4.06 min: -4.47 mean: -0.05 20%|██ | 8/40 [00:06<00:24, 1.31it/s] timestep: 780 max: 4.06 min: -4.48 mean:-0.05 22%|██▎ | 9/40 [00:06<00:23, 1.31it/s] timestep: 761 max: 4.04 min: -4.48 mean: -0.06 25%|██▌ | 10/40 [00:07<00:22, 1.31it/s] timestep: 742 max: 4.04 min: -4.49 mean: -0.07 28%|██▊ | 11/40 [00:08<00:22, 1.31it/s] timestep: 723 max: 4.04 min: -4.49 mean: -0.07 30%|███ | 12/40 [00:09<00:21, 1.31it/s] timestep: 704 max: 4.04 min: -4.5 mean: -0.08 32%|███▎ | 13/40 [00:09<00:20, 1.31it/s] timestep: 685 max: 4.04 min: -4.5 mean: -0.08 35%|███▌ | 14/40 [00:10<00:19, 1.31it/s] timestep: 666 max: 4.04 min: -4.5 mean: -0.09 38%|███▊ | 15/40 [00:11<00:19, 1.31it/s] timestep: 647 max: 4.04 min: -4.5 mean: -0.1 40%|████ | 16/40 [00:12<00:18, 1.31it/s] timestep: 628 max: 4.03 min: -4.5 mean: -0.1 42%|████▎ | 17/40 [00:13<00:17, 1.31it/s] timestep: 609 max: 4.01 min: -4.49 mean: -0.11 45%|████▌ | 18/40 [00:13<00:16, 1.31it/s] timestep: 590 max: 4.0 min: -4.48 mean: -0.11 48%|████▊ | 19/40 [00:14<00:16, 1.31it/s] timestep: 571 max: 3.98 min: -4.47 mean: -0.12 50%|█████ | 20/40 [00:15<00:15, 1.31it/s] timestep: 552 max: 3.95 min: -4.45 mean: -0.12 52%|█████▎ | 21/40 [00:16<00:14, 1.31it/s] timestep: 533 max: 3.93 min: -4.43 mean: -0.13 55%|█████▌ | 22/40 [00:16<00:13, 1.31it/s] timestep: 514 max: 3.9 min: -4.41 mean: -0.13 57%|█████▊ | 23/40 [00:17<00:13, 1.31it/s] timestep: 495 max: 3.87 min: -4.38 mean: -0.14 60%|██████ | 24/40 [00:18<00:12, 1.31it/s] timestep: 476 max: 3.83 min: -4.34 mean: -0.14 62%|██████▎ | 25/40 [00:19<00:11, 1.31it/s] timestep: 457 max: 3.79 min: -4.31 mean: -0.14 65%|██████▌ | 26/40 [00:19<00:10, 1.31it/s] timestep: 438 max: 3.74 min: -4.26 mean: -0.15 68%|██████▊ | 27/40 [00:20<00:09, 1.31it/s] timestep: 419 max: 3.69 min: -4.21 mean: -0.15 70%|███████ | 28/40 [00:21<00:09, 1.31it/s] timestep: 400 max: 3.63 min: -4.16 mean: -0.15 72%|███████▎ | 29/40 [00:22<00:08, 1.31it/s] timestep: 381 max: 3.56 min: -4.1 mean: -0.16 75%|███████▌ | 30/40 [00:22<00:07, 1.31it/s] timestep: 362 max: 3.54 min: -4.04 mean: -0.16 78%|███████▊ | 31/40 [00:23<00:06, 1.30it/s] timestep: 343 max: 3.51 min: -3.98 mean: -0.16 80%|████████ | 32/40 [00:24<00:06, 1.31it/s] timestep: 324 max: 3.48 min: -3.93 mean: -0.16 82%|████████▎ | 33/40 [00:25<00:05, 1.31it/s] timestep: 305 max: 3.47 min: -3.89 mean: -0.17 85%|████████▌ | 34/40 [00:26<00:04, 1.31it/s] timestep: 286 max: 3.46 min: -3.86 mean: -0.17 88%|████████▊ | 35/40 [00:26<00:03, 1.30it/s] timestep: 267 max: 3.46 min: -3.81 mean: -0.17 90%|█████████ | 36/40 [00:27<00:03, 1.31it/s] timestep: 248 max: 3.45 min: -3.77 mean: -0.17 92%|█████████▎| 37/40 [00:28<00:02, 1.31it/s] timestep: 229 max: 3.44 min: -3.72 mean: -0.17 95%|█████████▌| 38/40 [00:29<00:01, 1.31it/s] timestep: 210 max: 3.42 min: -3.66 mean: -0.17 98%|█████████▊| 39/40 [00:29<00:00, 1.31it/s] 100%|██████████| 40/40 [00:30<00:00, 1.31it/s] 100%|██████████| 40/40 [00:30<00:00, 1.31it/s] timestep: 181 max: 3.3 min: -3.52 mean: -0.17 0%| | 0/10 [00:00<?, ?it/s] timestep: 161 max: 3.21 min: -3.38 mean: -0.17 10%|█ | 1/10 [00:00<00:05, 1.59it/s] timestep: 141 max: 3.17 min: -3.24 mean: -0.17 20%|██ | 2/10 [00:01<00:05, 1.59it/s] timestep: 121 max: 3.13 min: -3.11 mean: -0.17 30%|███ | 3/10 [00:01<00:04, 1.59it/s] timestep: 101 max: 3.09 min: -2.97 mean: -0.17 40%|████ | 4/10 [00:02<00:03, 1.59it/s] timestep: 81 max: 3.04 min: -2.89 mean: -0.17 50%|█████ | 5/10 [00:03<00:03, 1.59it/s] timestep: 61 max: 3.0 min: -2.82 mean: -0.17 60%|██████ | 6/10 [00:03<00:02, 1.59it/s] timestep: 41 max: 2.95 min: -2.73 mean: -0.17 70%|███████ | 7/10 [00:04<00:01, 1.59it/s] timestep: 21 max: 2.99 min: -2.61 mean: -0.17 80%|████████ | 8/10 [00:05<00:01, 1.59it/s] timestep: 1 max: 3.02 min: -2.58 mean: -0.17 90%|█████████ | 9/10 [00:05<00:00, 1.59it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] Inference took: 41.25201749801636 12700Prediction
alexgenovese/sdxl-custom-model:ecde520aID3uwthblbvftpx6prpq4cjsczvyStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a close up (analog style, dreamy portrait) (saturation:0.3), of a female, (gazing into the distance), posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast), analog style, dramatic lighting, atmospheric
- refiner
- true
- denoising
- 0.8
- seed_number
- 12345
- guidance_scale
- 7
- negative_prompt
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a close up (analog style, dreamy portrait) (saturation:0.3), of a female, (gazing into the distance), posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast), analog style, dramatic lighting, atmospheric", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "a close up (analog style, dreamy portrait) (saturation:0.3), of a female, (gazing into the distance), posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast), analog style, dramatic lighting, atmospheric", guidance_scale: 7, negative_prompt: "", num_inference_steps: 50 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "a close up (analog style, dreamy portrait) (saturation:0.3), of a female, (gazing into the distance), posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast), analog style, dramatic lighting, atmospheric", "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "a close up (analog style, dreamy portrait) (saturation:0.3), of a female, (gazing into the distance), posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast), analog style, dramatic lighting, atmospheric", "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a close up (analog style, dreamy portrait) (saturation:0.3), of a female, (gazing into the distance), posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast), analog style, dramatic lighting, atmospheric"' \ -i 'guidance_scale=7' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a close up (analog style, dreamy portrait) (saturation:0.3), of a female, (gazing into the distance), posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast), analog style, dramatic lighting, atmospheric", "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-19T12:22:34.929686Z", "created_at": "2023-11-19T12:21:53.390554Z", "data_removed": false, "error": null, "id": "3uwthblbvftpx6prpq4cjsczvy", "input": { "width": 1024, "height": 1024, "prompt": "a close up (analog style, dreamy portrait) (saturation:0.3), of a female, (gazing into the distance), posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast), analog style, dramatic lighting, atmospheric", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 }, "logs": "Starting fp16 torch.float32 cuda\nThe current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported.\nFused all loras in UNet\nApplied correction to prompts positive a close up (analog style, dreamy portrait)1.10 (saturation)0.30, of a female, (gazing into the distance)1.10, posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast)1.10, analog style, dramatic lighting, atmospheric, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 951 max: 4.01 min: -4.31 mean: -0.02\n 0%| | 0/40 [00:00<?, ?it/s]\ntimestep: 932 max: 4.01 min: -4.32 mean: -0.02\n 2%|▎ | 1/40 [00:00<00:29, 1.31it/s]\ntimestep: 913 max: 4.01 min: -4.32 mean: -0.03\n 5%|▌ | 2/40 [00:01<00:29, 1.31it/s]\ntimestep: 894 max: 3.98 min: -4.33 mean: -0.03\n 8%|▊ | 3/40 [00:02<00:28, 1.31it/s]\ntimestep: 875 max: 3.98 min: -4.34 mean: -0.03\n 10%|█ | 4/40 [00:03<00:27, 1.31it/s]\ntimestep: 856 max: 3.95 min: -4.34 mean: -0.04\n 12%|█▎ | 5/40 [00:03<00:26, 1.31it/s]\ntimestep: 837 max: 3.94 min: -4.34 mean: -0.04\n 15%|█▌ | 6/40 [00:04<00:26, 1.31it/s]\ntimestep: 818 max: 3.92 min: -4.33 mean: -0.05\n 18%|█▊ | 7/40 [00:05<00:25, 1.31it/s]\ntimestep: 799 max: 3.9 min: -4.33 mean: -0.05\n 20%|██ | 8/40 [00:06<00:24, 1.30it/s]\ntimestep: 780 max: 3.89 min: -4.32 mean: -0.05\n 22%|██▎ | 9/40 [00:06<00:23, 1.31it/s]\ntimestep: 761 max: 3.88 min: -4.32 mean: -0.06\n 25%|██▌ | 10/40 [00:07<00:22, 1.31it/s]\ntimestep: 742 max: 3.87 min: -4.31 mean: -0.06\n 28%|██▊ | 11/40 [00:08<00:22, 1.31it/s]\ntimestep: 723 max: 3.86 min: -4.3 mean: -0.07\n 30%|███ | 12/40 [00:09<00:21, 1.31it/s]\ntimestep: 704 max: 3.84 min: -4.29 mean: -0.07\n 32%|███▎ | 13/40 [00:09<00:20, 1.31it/s]\ntimestep: 685 max: 3.82 min: -4.28 mean: -0.08\n 35%|███▌ | 14/40 [00:10<00:19, 1.31it/s]\ntimestep: 666 max: 3.8 min: -4.27 mean: -0.08\n 38%|███▊ | 15/40 [00:11<00:19, 1.31it/s]\ntimestep: 647 max: 3.78 min: -4.25 mean: -0.09\n 40%|████ | 16/40 [00:12<00:18, 1.31it/s]\ntimestep: 628 max: 3.75 min: -4.23 mean: -0.09\n 42%|████▎ | 17/40 [00:13<00:17, 1.31it/s]\ntimestep: 609 max: 3.73 min: -4.21 mean: -0.1\n 45%|████▌ | 18/40 [00:13<00:16, 1.31it/s]\ntimestep: 590 max: 3.7 min: -4.19 mean: -0.11\n 48%|████▊ | 19/40 [00:14<00:16, 1.31it/s]\ntimestep: 571 max: 3.68 min: -4.16 mean: -0.11\n 50%|█████ | 20/40 [00:15<00:15, 1.31it/s]\ntimestep: 552 max: 3.65 min: -4.14 mean: -0.11\n 52%|█████▎ | 21/40 [00:16<00:14, 1.31it/s]\ntimestep: 533 max: 3.62 min: -4.11 mean: -0.12\n 55%|█████▌ | 22/40 [00:16<00:13, 1.31it/s]\ntimestep: 514 max: 3.58 min: -4.1 mean: -0.12\n 57%|█████▊ | 23/40 [00:17<00:13, 1.31it/s]\ntimestep: 495 max: 3.55 min: -4.09 mean: -0.13\n 60%|██████ | 24/40 [00:18<00:12, 1.31it/s]\ntimestep: 476 max: 3.51 min: -4.08 mean: -0.13\n 62%|██████▎ | 25/40 [00:19<00:11, 1.31it/s]\ntimestep: 457 max: 3.46 min: -4.07 mean: -0.14\n 65%|██████▌ | 26/40 [00:19<00:10, 1.31it/s]\ntimestep: 438 max: 3.41 min: -4.06 mean: -0.14\n 68%|██████▊ | 27/40 [00:20<00:09, 1.31it/s]\ntimestep: 419 max: 3.36 min: -4.04 mean: -0.14\n 70%|███████ | 28/40 [00:21<00:09, 1.31it/s]\ntimestep: 400 max: 3.31 min: -4.02 mean: -0.15\n 72%|███████▎ | 29/40 [00:22<00:08, 1.31it/s]\ntimestep: 381 max: 3.31 min: -4.0 mean: -0.15\n 75%|███████▌ | 30/40 [00:22<00:07, 1.31it/s]\ntimestep: 362 max: 3.31 min: -3.97 mean: -0.15\n 78%|███████▊ | 31/40 [00:23<00:06, 1.30it/s]\ntimestep: 343 max: 3.31 min: -3.94 mean: -0.16\n 80%|████████ | 32/40 [00:24<00:06, 1.31it/s]\ntimestep: 324 max: 3.3 min: -3.91 mean: -0.16\n 82%|████████▎ | 33/40 [00:25<00:05, 1.31it/s]\ntimestep: 305 max: 3.29 min: -3.87 mean: -0.16\n 85%|████████▌ | 34/40 [00:26<00:04, 1.31it/s]\ntimestep: 286 max: 3.27 min: -3.84 mean: -0.17\n 88%|████████▊ | 35/40 [00:26<00:03, 1.31it/s]\ntimestep: 267 max: 3.26 min: -3.8 mean: -0.17\n 90%|█████████ | 36/40 [00:27<00:03, 1.31it/s]\ntimestep: 248 max: 3.24 min: -3.76 mean: -0.17\n 92%|█████████▎| 37/40 [00:28<00:02, 1.31it/s]\ntimestep: 229 max: 3.22 min: -3.71 mean: -0.17\n 95%|█████████▌| 38/40 [00:29<00:01, 1.31it/s]\ntimestep: 210 max: 3.2 min: -3.67 mean: -0.17\n 98%|█████████▊| 39/40 [00:29<00:00, 1.31it/s]\n100%|██████████| 40/40 [00:30<00:00, 1.31it/s]\n100%|██████████| 40/40 [00:30<00:00, 1.31it/s]\ntimestep: 181 max: 3.12 min: -3.53 mean: -0.18\n 0%| | 0/10 [00:00<?, ?it/s]\ntimestep: 161 max: 3.04 min: -3.41 mean: -0.18\n 10%|█ | 1/10 [00:00<00:05, 1.59it/s]\ntimestep: 141 max: 2.96 min: -3.28 mean: -0.18\n 20%|██ | 2/10 [00:01<00:05, 1.59it/s]\ntimestep: 121 max: 2.88 min: -3.16 mean:-0.18\n 30%|███ | 3/10 [00:01<00:04, 1.59it/s]\ntimestep: 101 max: 2.8 min: -3.05 mean: -0.18\n 40%|████ | 4/10 [00:02<00:03, 1.59it/s]\ntimestep: 81 max: 2.72 min: -2.93 mean:-0.18\n 50%|█████ | 5/10 [00:03<00:03, 1.59it/s]\ntimestep: 61 max: 2.64 min: -2.8 mean: -0.18\n 60%|██████ | 6/10 [00:03<00:02, 1.59it/s]\ntimestep: 41 max: 2.54 min: -2.66mean: -0.18\n 70%|███████ | 7/10 [00:04<00:01, 1.59it/s]\ntimestep: 21 max: 2.39 min: -2.45 mean: -0.18\n 80%|████████ | 8/10 [00:05<00:01, 1.59it/s]\ntimestep: 1 max: 2.35 min: -2.4 mean: -0.18\n 90%|█████████ | 9/10 [00:05<00:00, 1.59it/s]\n100%|██████████| 10/10 [00:06<00:00, 1.59it/s]\n100%|██████████| 10/10 [00:06<00:00, 1.59it/s]\nInference took: 41.16629600524902 30749", "metrics": { "predict_time": 41.525267, "total_time": 41.539132 }, "output": "https://replicate.delivery/pbxt/IlwnbJH6BM5OJBpi7SPDJZqNVTTbtzwdGuq9rrk1qJmCwe8IA/image-30749-40.513755798339844.png", "started_at": "2023-11-19T12:21:53.404419Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3uwthblbvftpx6prpq4cjsczvy", "cancel": "https://api.replicate.com/v1/predictions/3uwthblbvftpx6prpq4cjsczvy/cancel" }, "version": "a08504bd6b123bb993f648c6361041a3cc3f721a24ab6a1619b10f03dd8c0dff" }Generated inStarting fp16 torch.float32 cuda The current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported. Fused all loras in UNet Applied correction to prompts positive a close up (analog style, dreamy portrait)1.10 (saturation)0.30, of a female, (gazing into the distance)1.10, posing on a cobble stone street in a scenic Italian rural landscape, windy, scenic sunset, perfect anatomy, (low contrast)1.10, analog style, dramatic lighting, atmospheric, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 951 max: 4.01 min: -4.31 mean: -0.02 0%| | 0/40 [00:00<?, ?it/s] timestep: 932 max: 4.01 min: -4.32 mean: -0.02 2%|▎ | 1/40 [00:00<00:29, 1.31it/s] timestep: 913 max: 4.01 min: -4.32 mean: -0.03 5%|▌ | 2/40 [00:01<00:29, 1.31it/s] timestep: 894 max: 3.98 min: -4.33 mean: -0.03 8%|▊ | 3/40 [00:02<00:28, 1.31it/s] timestep: 875 max: 3.98 min: -4.34 mean: -0.03 10%|█ | 4/40 [00:03<00:27, 1.31it/s] timestep: 856 max: 3.95 min: -4.34 mean: -0.04 12%|█▎ | 5/40 [00:03<00:26, 1.31it/s] timestep: 837 max: 3.94 min: -4.34 mean: -0.04 15%|█▌ | 6/40 [00:04<00:26, 1.31it/s] timestep: 818 max: 3.92 min: -4.33 mean: -0.05 18%|█▊ | 7/40 [00:05<00:25, 1.31it/s] timestep: 799 max: 3.9 min: -4.33 mean: -0.05 20%|██ | 8/40 [00:06<00:24, 1.30it/s] timestep: 780 max: 3.89 min: -4.32 mean: -0.05 22%|██▎ | 9/40 [00:06<00:23, 1.31it/s] timestep: 761 max: 3.88 min: -4.32 mean: -0.06 25%|██▌ | 10/40 [00:07<00:22, 1.31it/s] timestep: 742 max: 3.87 min: -4.31 mean: -0.06 28%|██▊ | 11/40 [00:08<00:22, 1.31it/s] timestep: 723 max: 3.86 min: -4.3 mean: -0.07 30%|███ | 12/40 [00:09<00:21, 1.31it/s] timestep: 704 max: 3.84 min: -4.29 mean: -0.07 32%|███▎ | 13/40 [00:09<00:20, 1.31it/s] timestep: 685 max: 3.82 min: -4.28 mean: -0.08 35%|███▌ | 14/40 [00:10<00:19, 1.31it/s] timestep: 666 max: 3.8 min: -4.27 mean: -0.08 38%|███▊ | 15/40 [00:11<00:19, 1.31it/s] timestep: 647 max: 3.78 min: -4.25 mean: -0.09 40%|████ | 16/40 [00:12<00:18, 1.31it/s] timestep: 628 max: 3.75 min: -4.23 mean: -0.09 42%|████▎ | 17/40 [00:13<00:17, 1.31it/s] timestep: 609 max: 3.73 min: -4.21 mean: -0.1 45%|████▌ | 18/40 [00:13<00:16, 1.31it/s] timestep: 590 max: 3.7 min: -4.19 mean: -0.11 48%|████▊ | 19/40 [00:14<00:16, 1.31it/s] timestep: 571 max: 3.68 min: -4.16 mean: -0.11 50%|█████ | 20/40 [00:15<00:15, 1.31it/s] timestep: 552 max: 3.65 min: -4.14 mean: -0.11 52%|█████▎ | 21/40 [00:16<00:14, 1.31it/s] timestep: 533 max: 3.62 min: -4.11 mean: -0.12 55%|█████▌ | 22/40 [00:16<00:13, 1.31it/s] timestep: 514 max: 3.58 min: -4.1 mean: -0.12 57%|█████▊ | 23/40 [00:17<00:13, 1.31it/s] timestep: 495 max: 3.55 min: -4.09 mean: -0.13 60%|██████ | 24/40 [00:18<00:12, 1.31it/s] timestep: 476 max: 3.51 min: -4.08 mean: -0.13 62%|██████▎ | 25/40 [00:19<00:11, 1.31it/s] timestep: 457 max: 3.46 min: -4.07 mean: -0.14 65%|██████▌ | 26/40 [00:19<00:10, 1.31it/s] timestep: 438 max: 3.41 min: -4.06 mean: -0.14 68%|██████▊ | 27/40 [00:20<00:09, 1.31it/s] timestep: 419 max: 3.36 min: -4.04 mean: -0.14 70%|███████ | 28/40 [00:21<00:09, 1.31it/s] timestep: 400 max: 3.31 min: -4.02 mean: -0.15 72%|███████▎ | 29/40 [00:22<00:08, 1.31it/s] timestep: 381 max: 3.31 min: -4.0 mean: -0.15 75%|███████▌ | 30/40 [00:22<00:07, 1.31it/s] timestep: 362 max: 3.31 min: -3.97 mean: -0.15 78%|███████▊ | 31/40 [00:23<00:06, 1.30it/s] timestep: 343 max: 3.31 min: -3.94 mean: -0.16 80%|████████ | 32/40 [00:24<00:06, 1.31it/s] timestep: 324 max: 3.3 min: -3.91 mean: -0.16 82%|████████▎ | 33/40 [00:25<00:05, 1.31it/s] timestep: 305 max: 3.29 min: -3.87 mean: -0.16 85%|████████▌ | 34/40 [00:26<00:04, 1.31it/s] timestep: 286 max: 3.27 min: -3.84 mean: -0.17 88%|████████▊ | 35/40 [00:26<00:03, 1.31it/s] timestep: 267 max: 3.26 min: -3.8 mean: -0.17 90%|█████████ | 36/40 [00:27<00:03, 1.31it/s] timestep: 248 max: 3.24 min: -3.76 mean: -0.17 92%|█████████▎| 37/40 [00:28<00:02, 1.31it/s] timestep: 229 max: 3.22 min: -3.71 mean: -0.17 95%|█████████▌| 38/40 [00:29<00:01, 1.31it/s] timestep: 210 max: 3.2 min: -3.67 mean: -0.17 98%|█████████▊| 39/40 [00:29<00:00, 1.31it/s] 100%|██████████| 40/40 [00:30<00:00, 1.31it/s] 100%|██████████| 40/40 [00:30<00:00, 1.31it/s] timestep: 181 max: 3.12 min: -3.53 mean: -0.18 0%| | 0/10 [00:00<?, ?it/s] timestep: 161 max: 3.04 min: -3.41 mean: -0.18 10%|█ | 1/10 [00:00<00:05, 1.59it/s] timestep: 141 max: 2.96 min: -3.28 mean: -0.18 20%|██ | 2/10 [00:01<00:05, 1.59it/s] timestep: 121 max: 2.88 min: -3.16 mean:-0.18 30%|███ | 3/10 [00:01<00:04, 1.59it/s] timestep: 101 max: 2.8 min: -3.05 mean: -0.18 40%|████ | 4/10 [00:02<00:03, 1.59it/s] timestep: 81 max: 2.72 min: -2.93 mean:-0.18 50%|█████ | 5/10 [00:03<00:03, 1.59it/s] timestep: 61 max: 2.64 min: -2.8 mean: -0.18 60%|██████ | 6/10 [00:03<00:02, 1.59it/s] timestep: 41 max: 2.54 min: -2.66mean: -0.18 70%|███████ | 7/10 [00:04<00:01, 1.59it/s] timestep: 21 max: 2.39 min: -2.45 mean: -0.18 80%|████████ | 8/10 [00:05<00:01, 1.59it/s] timestep: 1 max: 2.35 min: -2.4 mean: -0.18 90%|█████████ | 9/10 [00:05<00:00, 1.59it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] Inference took: 41.16629600524902 30749Prediction
alexgenovese/sdxl-custom-model:ecde520aIDzqb4m5tbb4mvn72aquh7g4vaaiStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays
- refiner
- true
- denoising
- 0.8
- seed_number
- 12345
- guidance_scale
- 7
- negative_prompt
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays", guidance_scale: 7, negative_prompt: "", num_inference_steps: 50 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays", "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays", "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays"' \ -i 'guidance_scale=7' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays", "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-19T12:23:25.696676Z", "created_at": "2023-11-19T12:22:44.201433Z", "data_removed": false, "error": null, "id": "zqb4m5tbb4mvn72aquh7g4vaai", "input": { "width": 1024, "height": 1024, "prompt": "masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 7, "negative_prompt": "", "num_inference_steps": 50 }, "logs": "Starting fp16 torch.float32 cuda\nThe current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported.\nFused all loras in UNet\nApplied correction to prompts positive masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 951 max: 4.03 min: -4.29 mean: -0.01\n 0%| | 0/40 [00:00<?, ?it/s]\ntimestep: 932 max: 4.01 min: -4.28mean: -0.0\n 2%|▎ | 1/40 [00:00<00:29, 1.31it/s]\ntimestep: 913 max: 4.01 min: -4.27 mean: -0.01\n 5%|▌ | 2/40 [00:01<00:29, 1.31it/s]\ntimestep: 894 max: 4.0 min: -4.27mean: -0.01\n 8%|▊ | 3/40 [00:02<00:28, 1.31it/s]\ntimestep: 875 max: 3.98 min: -4.27 mean:-0.01\n 10%|█ | 4/40 [00:03<00:27, 1.31it/s]\ntimestep: 856 max: 3.96 min: -4.26 mean: -0.01\n 12%|█▎ | 5/40 [00:03<00:26, 1.31it/s]\ntimestep: 837 max: 3.95 min: -4.26 mean: -0.01\n 15%|█▌ | 6/40 [00:04<00:26, 1.30it/s]\ntimestep: 818 max: 3.93 min: -4.25 mean: -0.01\n 18%|█▊ | 7/40 [00:05<00:25, 1.30it/s]\ntimestep: 799 max: 3.92 min: -4.25 mean: -0.01\n 20%|██ | 8/40 [00:06<00:24, 1.31it/s]\ntimestep: 780 max: 3.9 min: -4.25 mean: -0.01\n 22%|██▎ | 9/40 [00:06<00:23, 1.31it/s]\ntimestep: 761 max: 3.89 min: -4.24 mean: -0.01\n 25%|██▌ | 10/40 [00:07<00:22, 1.31it/s]\ntimestep: 742 max: 3.87 min: -4.23 mean: -0.01\n 28%|██▊ | 11/40 [00:08<00:22, 1.31it/s]\ntimestep: 723 max: 3.85 min: -4.23 mean: -0.01\n 30%|███ | 12/40 [00:09<00:21, 1.31it/s]\ntimestep: 704 max: 3.83 min: -4.22 mean: -0.01\n 32%|███▎ | 13/40 [00:09<00:20, 1.31it/s]\ntimestep: 685 max: 3.81 min: -4.21 mean: -0.01\n 35%|███▌ | 14/40 [00:10<00:19, 1.31it/s]\ntimestep: 666 max: 3.79 min: -4.19 mean: -0.01\n 38%|███▊ | 15/40 [00:11<00:19, 1.31it/s]\ntimestep: 647 max: 3.76 min: -4.18 mean: -0.01\n 40%|████ | 16/40 [00:12<00:18, 1.31it/s]\ntimestep: 628 max: 3.74 min: -4.16 mean: -0.01\n 42%|████▎ | 17/40 [00:13<00:17, 1.31it/s]\ntimestep: 609 max: 3.71 min: -4.13 mean: -0.01\n 45%|████▌ | 18/40 [00:13<00:16, 1.31it/s]\ntimestep: 590 max: 3.71 min: -4.11 mean: -0.01\n 48%|████▊ | 19/40 [00:14<00:16, 1.31it/s]\ntimestep: 571 max: 3.72 min: -4.08 mean: -0.01\n 50%|█████ | 20/40 [00:15<00:15, 1.31it/s]\ntimestep: 552 max: 3.72 min: -4.05 mean: -0.01\n 52%|█████▎ | 21/40 [00:16<00:14, 1.31it/s]\ntimestep: 533 max: 3.72 min: -4.02 mean: -0.01\n 55%|█████▌ | 22/40 [00:16<00:13, 1.31it/s]\ntimestep: 514 max: 3.71 min: -3.99 mean: -0.0\n 57%|█████▊ | 23/40 [00:17<00:12, 1.31it/s]\ntimestep: 495 max: 3.71 min: -3.95 mean: -0.0\n 60%|██████ | 24/40 [00:18<00:12, 1.31it/s]\ntimestep: 476 max: 3.71 min: -3.94 mean: -0.0\n 62%|██████▎ | 25/40 [00:19<00:11, 1.31it/s]\ntimestep: 457 max: 3.7 min: -3.92 mean:-0.0\n 65%|██████▌ | 26/40 [00:19<00:10, 1.31it/s]\ntimestep: 438 max: 3.69 min: -3.89 mean: 0.0\n 68%|██████▊ | 27/40 [00:20<00:09, 1.31it/s]\ntimestep: 419 max: 3.68 min: -3.86 mean: 0.0\n 70%|███████ | 28/40 [00:21<00:09, 1.31it/s]\ntimestep: 400 max: 3.67 min: -3.83 mean: 0.0\n 72%|███████▎ | 29/40 [00:22<00:08, 1.31it/s]\ntimestep: 381 max: 3.66 min: -3.79 mean: 0.0\n 75%|███████▌ | 30/40 [00:22<00:07, 1.31it/s]\ntimestep: 362 max: 3.64 min: -3.75 mean: 0.01\n 78%|███████▊ | 31/40 [00:23<00:06, 1.31it/s]\ntimestep: 343 max: 3.63 min: -3.7 mean: 0.01\n 80%|████████ | 32/40 [00:24<00:06, 1.31it/s]\ntimestep: 324 max: 3.62 min: -3.66 mean: 0.01\n 82%|████████▎ | 33/40 [00:25<00:05, 1.31it/s]\ntimestep: 305 max: 3.6 min: -3.63 mean: 0.01\n 85%|████████▌ | 34/40 [00:26<00:04, 1.31it/s]\ntimestep: 286 max: 3.58 min: -3.61 mean: 0.01\n 88%|████████▊ | 35/40 [00:26<00:03, 1.31it/s]\ntimestep: 267 max: 3.55 min: -3.58 mean: 0.01\n 90%|█████████ | 36/40 [00:27<00:03, 1.31it/s]\ntimestep: 248 max: 3.52 min: -3.55 mean: 0.02\n 92%|█████████▎| 37/40 [00:28<00:02, 1.31it/s]\ntimestep: 229 max: 3.48 min: -3.51 mean: 0.02\n 95%|█████████▌| 38/40 [00:29<00:01, 1.31it/s]\ntimestep: 210 max: 3.44 min: -3.48 mean: 0.02\n 98%|█████████▊| 39/40 [00:29<00:00, 1.31it/s]\n100%|██████████| 40/40 [00:30<00:00, 1.31it/s]\n100%|██████████| 40/40 [00:30<00:00, 1.31it/s]\ntimestep: 181 max: 3.3 min: -3.36 mean: 0.02\n 0%| | 0/10 [00:00<?, ?it/s]\ntimestep: 161 max: 3.17 min: -3.25 mean: 0.02\n 10%|█ | 1/10 [00:00<00:05, 1.59it/s]\ntimestep: 141 max: 3.04 min: -3.14 mean: 0.02\n 20%|██ | 2/10 [00:01<00:05, 1.59it/s]\ntimestep: 121 max: 2.96 min: -3.1 mean: 0.02\n 30%|███ | 3/10 [00:01<00:04, 1.59it/s]\ntimestep: 101 max: 2.91 min: -3.07 mean:0.02\n 40%|████ | 4/10 [00:02<00:03, 1.59it/s]\ntimestep: 81 max: 2.88 min: -3.04 mean: 0.02\n 50%|█████ | 5/10 [00:03<00:03, 1.59it/s]\ntimestep: 61 max: 2.86 min: -3.0 mean: 0.02\n 60%|██████ | 6/10 [00:03<00:02, 1.59it/s]\ntimestep: 41 max: 2.84 min: -2.94 mean: 0.02\n 70%|███████ | 7/10 [00:04<00:01, 1.59it/s]\ntimestep: 21 max: 2.82 min: -2.83 mean: 0.02\n 80%|████████ | 8/10 [00:05<00:01, 1.59it/s]\ntimestep: 1 max: 2.82 min: -2.8 mean: 0.02\n 90%|█████████ | 9/10 [00:05<00:00, 1.59it/s]\n100%|██████████| 10/10 [00:06<00:00, 1.59it/s]\n100%|██████████| 10/10 [00:06<00:00, 1.59it/s]\nInference took: 41.02201986312866 3472", "metrics": { "predict_time": 41.437443, "total_time": 41.495243 }, "output": "https://replicate.delivery/pbxt/bbWF4bvSaZYxOFekoLy1W74yRkiSGuVKJarBPPANWC1eA75RA/image-3472-40.380552768707275.png", "started_at": "2023-11-19T12:22:44.259233Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/zqb4m5tbb4mvn72aquh7g4vaai", "cancel": "https://api.replicate.com/v1/predictions/zqb4m5tbb4mvn72aquh7g4vaai/cancel" }, "version": "a08504bd6b123bb993f648c6361041a3cc3f721a24ab6a1619b10f03dd8c0dff" }Generated inStarting fp16 torch.float32 cuda The current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported. Fused all loras in UNet Applied correction to prompts positive masterpiece, close up portrait, woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a hyperrealistic girl, perfect slim body, hyperrealistic schoolgirl, dressed like bitch , realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 951 max: 4.03 min: -4.29 mean: -0.01 0%| | 0/40 [00:00<?, ?it/s] timestep: 932 max: 4.01 min: -4.28mean: -0.0 2%|▎ | 1/40 [00:00<00:29, 1.31it/s] timestep: 913 max: 4.01 min: -4.27 mean: -0.01 5%|▌ | 2/40 [00:01<00:29, 1.31it/s] timestep: 894 max: 4.0 min: -4.27mean: -0.01 8%|▊ | 3/40 [00:02<00:28, 1.31it/s] timestep: 875 max: 3.98 min: -4.27 mean:-0.01 10%|█ | 4/40 [00:03<00:27, 1.31it/s] timestep: 856 max: 3.96 min: -4.26 mean: -0.01 12%|█▎ | 5/40 [00:03<00:26, 1.31it/s] timestep: 837 max: 3.95 min: -4.26 mean: -0.01 15%|█▌ | 6/40 [00:04<00:26, 1.30it/s] timestep: 818 max: 3.93 min: -4.25 mean: -0.01 18%|█▊ | 7/40 [00:05<00:25, 1.30it/s] timestep: 799 max: 3.92 min: -4.25 mean: -0.01 20%|██ | 8/40 [00:06<00:24, 1.31it/s] timestep: 780 max: 3.9 min: -4.25 mean: -0.01 22%|██▎ | 9/40 [00:06<00:23, 1.31it/s] timestep: 761 max: 3.89 min: -4.24 mean: -0.01 25%|██▌ | 10/40 [00:07<00:22, 1.31it/s] timestep: 742 max: 3.87 min: -4.23 mean: -0.01 28%|██▊ | 11/40 [00:08<00:22, 1.31it/s] timestep: 723 max: 3.85 min: -4.23 mean: -0.01 30%|███ | 12/40 [00:09<00:21, 1.31it/s] timestep: 704 max: 3.83 min: -4.22 mean: -0.01 32%|███▎ | 13/40 [00:09<00:20, 1.31it/s] timestep: 685 max: 3.81 min: -4.21 mean: -0.01 35%|███▌ | 14/40 [00:10<00:19, 1.31it/s] timestep: 666 max: 3.79 min: -4.19 mean: -0.01 38%|███▊ | 15/40 [00:11<00:19, 1.31it/s] timestep: 647 max: 3.76 min: -4.18 mean: -0.01 40%|████ | 16/40 [00:12<00:18, 1.31it/s] timestep: 628 max: 3.74 min: -4.16 mean: -0.01 42%|████▎ | 17/40 [00:13<00:17, 1.31it/s] timestep: 609 max: 3.71 min: -4.13 mean: -0.01 45%|████▌ | 18/40 [00:13<00:16, 1.31it/s] timestep: 590 max: 3.71 min: -4.11 mean: -0.01 48%|████▊ | 19/40 [00:14<00:16, 1.31it/s] timestep: 571 max: 3.72 min: -4.08 mean: -0.01 50%|█████ | 20/40 [00:15<00:15, 1.31it/s] timestep: 552 max: 3.72 min: -4.05 mean: -0.01 52%|█████▎ | 21/40 [00:16<00:14, 1.31it/s] timestep: 533 max: 3.72 min: -4.02 mean: -0.01 55%|█████▌ | 22/40 [00:16<00:13, 1.31it/s] timestep: 514 max: 3.71 min: -3.99 mean: -0.0 57%|█████▊ | 23/40 [00:17<00:12, 1.31it/s] timestep: 495 max: 3.71 min: -3.95 mean: -0.0 60%|██████ | 24/40 [00:18<00:12, 1.31it/s] timestep: 476 max: 3.71 min: -3.94 mean: -0.0 62%|██████▎ | 25/40 [00:19<00:11, 1.31it/s] timestep: 457 max: 3.7 min: -3.92 mean:-0.0 65%|██████▌ | 26/40 [00:19<00:10, 1.31it/s] timestep: 438 max: 3.69 min: -3.89 mean: 0.0 68%|██████▊ | 27/40 [00:20<00:09, 1.31it/s] timestep: 419 max: 3.68 min: -3.86 mean: 0.0 70%|███████ | 28/40 [00:21<00:09, 1.31it/s] timestep: 400 max: 3.67 min: -3.83 mean: 0.0 72%|███████▎ | 29/40 [00:22<00:08, 1.31it/s] timestep: 381 max: 3.66 min: -3.79 mean: 0.0 75%|███████▌ | 30/40 [00:22<00:07, 1.31it/s] timestep: 362 max: 3.64 min: -3.75 mean: 0.01 78%|███████▊ | 31/40 [00:23<00:06, 1.31it/s] timestep: 343 max: 3.63 min: -3.7 mean: 0.01 80%|████████ | 32/40 [00:24<00:06, 1.31it/s] timestep: 324 max: 3.62 min: -3.66 mean: 0.01 82%|████████▎ | 33/40 [00:25<00:05, 1.31it/s] timestep: 305 max: 3.6 min: -3.63 mean: 0.01 85%|████████▌ | 34/40 [00:26<00:04, 1.31it/s] timestep: 286 max: 3.58 min: -3.61 mean: 0.01 88%|████████▊ | 35/40 [00:26<00:03, 1.31it/s] timestep: 267 max: 3.55 min: -3.58 mean: 0.01 90%|█████████ | 36/40 [00:27<00:03, 1.31it/s] timestep: 248 max: 3.52 min: -3.55 mean: 0.02 92%|█████████▎| 37/40 [00:28<00:02, 1.31it/s] timestep: 229 max: 3.48 min: -3.51 mean: 0.02 95%|█████████▌| 38/40 [00:29<00:01, 1.31it/s] timestep: 210 max: 3.44 min: -3.48 mean: 0.02 98%|█████████▊| 39/40 [00:29<00:00, 1.31it/s] 100%|██████████| 40/40 [00:30<00:00, 1.31it/s] 100%|██████████| 40/40 [00:30<00:00, 1.31it/s] timestep: 181 max: 3.3 min: -3.36 mean: 0.02 0%| | 0/10 [00:00<?, ?it/s] timestep: 161 max: 3.17 min: -3.25 mean: 0.02 10%|█ | 1/10 [00:00<00:05, 1.59it/s] timestep: 141 max: 3.04 min: -3.14 mean: 0.02 20%|██ | 2/10 [00:01<00:05, 1.59it/s] timestep: 121 max: 2.96 min: -3.1 mean: 0.02 30%|███ | 3/10 [00:01<00:04, 1.59it/s] timestep: 101 max: 2.91 min: -3.07 mean:0.02 40%|████ | 4/10 [00:02<00:03, 1.59it/s] timestep: 81 max: 2.88 min: -3.04 mean: 0.02 50%|█████ | 5/10 [00:03<00:03, 1.59it/s] timestep: 61 max: 2.86 min: -3.0 mean: 0.02 60%|██████ | 6/10 [00:03<00:02, 1.59it/s] timestep: 41 max: 2.84 min: -2.94 mean: 0.02 70%|███████ | 7/10 [00:04<00:01, 1.59it/s] timestep: 21 max: 2.82 min: -2.83 mean: 0.02 80%|████████ | 8/10 [00:05<00:01, 1.59it/s] timestep: 1 max: 2.82 min: -2.8 mean: 0.02 90%|█████████ | 9/10 [00:05<00:00, 1.59it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] 100%|██████████| 10/10 [00:06<00:00, 1.59it/s] Inference took: 41.02201986312866 3472Prediction
alexgenovese/sdxl-custom-model:ecde520aID3zmjevtbpcawxhbkgsvosoz3faStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, ((full body))
- refiner
- true
- denoising
- 0.8
- seed_number
- 12345
- guidance_scale
- 10
- negative_prompt
- num_inference_steps
- 35
{ "width": 1024, "height": 1024, "prompt": "a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, ((full body))", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, ((full body))", guidance_scale: 10, negative_prompt: "", num_inference_steps: 35 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, ((full body))", "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, ((full body))", "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, ((full body))"' \ -i 'guidance_scale=10' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=35'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, ((full body))", "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-19T12:24:30.440248Z", "created_at": "2023-11-19T12:23:59.487042Z", "data_removed": false, "error": null, "id": "3zmjevtbpcawxhbkgsvosoz3fa", "input": { "width": 1024, "height": 1024, "prompt": "a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, ((full body))", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 }, "logs": "Starting fp16 torch.float32 cuda\nThe current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported.\nFused all loras in UNet\nApplied correction to prompts positive a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, (full body)1.21, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 946 max: 4.06 min: -4.28 mean: -0.02\n 0%| | 0/28 [00:00<?, ?it/s]\ntimestep: 919 max: 4.01 min: -4.31 mean: 0.01\n 4%|▎ | 1/28 [00:00<00:20, 1.31it/s]\ntimestep: 892 max: 4.07 min: -4.24 mean: -0.03\n 7%|▋ | 2/28 [00:01<00:19, 1.31it/s]\ntimestep: 865 max: 4.03 min: -4.27 mean: -0.0\n 11%|█ | 3/28 [00:02<00:19, 1.31it/s]\ntimestep: 838 max: 4.05 min: -4.2 mean: -0.04\n 14%|█▍ | 4/28 [00:03<00:18, 1.31it/s]\ntimestep: 811 max: 4.02 min: -4.21 mean: -0.02\n 18%|█▊ | 5/28 [00:03<00:17, 1.31it/s]\ntimestep: 784 max: 4.01 min: -4.19 mean: -0.04\n 21%|██▏ | 6/28 [00:04<00:16, 1.31it/s]\ntimestep: 757 max: 4.0 min: -4.19 mean: -0.03\n 25%|██▌ | 7/28 [00:05<00:16, 1.31it/s]\ntimestep: 730 max: 3.96 min: -4.26 mean: -0.04\n 29%|██▊ | 8/28 [00:06<00:15, 1.31it/s]\ntimestep: 703 max: 3.96 min: -4.27 mean: -0.03\n 32%|███▏ | 9/28 [00:06<00:14, 1.31it/s]\ntimestep: 676 max: 3.95 min: -4.31 mean: -0.04\n 36%|███▌ | 10/28 [00:07<00:13, 1.31it/s]\ntimestep: 649 max: 3.99 min: -4.31 mean: -0.04\n 39%|███▉ | 11/28 [00:08<00:13, 1.31it/s]\ntimestep: 622 max: 4.01 min: -4.34 mean: -0.04\n 43%|████▎ | 12/28 [00:09<00:12, 1.31it/s]\ntimestep: 595 max: 4.04 min: -4.34 mean: -0.04\n 46%|████▋ | 13/28 [00:09<00:11, 1.31it/s]\ntimestep: 568 max: 4.05 min: -4.34 mean: -0.04\n 50%|█████ | 14/28 [00:10<00:10, 1.31it/s]\ntimestep: 541 max: 4.06 min: -4.32 mean: -0.04\n 54%|█████▎ | 15/28 [00:11<00:09, 1.31it/s]\ntimestep: 514 max: 4.06 min: -4.3 mean: -0.04\n 57%|█████▋ | 16/28 [00:12<00:09, 1.30it/s]\ntimestep: 487 max: 4.06 min: -4.28 mean: -0.04\n 61%|██████ | 17/28 [00:13<00:08, 1.31it/s]\ntimestep: 460 max: 4.04 min: -4.24mean: -0.04\n 64%|██████▍ | 18/28 [00:13<00:07, 1.31it/s]\ntimestep: 433 max: 4.03 min: -4.19 mean: -0.03\n 68%|██████▊ | 19/28 [00:14<00:06, 1.31it/s]\ntimestep: 406 max: 4.0 min: -4.13 mean: -0.03\n 71%|███████▏ | 20/28 [00:15<00:06, 1.31it/s]\ntimestep: 379 max: 3.97 min: -4.06 mean: -0.03\n 75%|███████▌ | 21/28 [00:16<00:05, 1.31it/s]\ntimestep: 352 max: 3.93 min: -3.98 mean: -0.03\n 79%|███████▊ | 22/28 [00:16<00:04, 1.31it/s]\ntimestep: 325 max: 3.88 min: -3.89 mean: -0.02\n 82%|████████▏ | 23/28 [00:17<00:03, 1.31it/s]\ntimestep: 298 max: 3.83 min: -3.82 mean: -0.02\n 86%|████████▌ | 24/28 [00:18<00:03, 1.31it/s]\ntimestep: 271 max: 3.76 min: -3.8 mean: -0.02\n 89%|████████▉ | 25/28 [00:19<00:02, 1.31it/s]\ntimestep: 244 max: 3.69 min: -3.78 mean: -0.01\n 93%|█████████▎| 26/28 [00:19<00:01, 1.31it/s]\ntimestep: 217 max: 3.61 min: -3.75 mean: -0.01\n 96%|█████████▋| 27/28 [00:20<00:00, 1.31it/s]\n100%|██████████| 28/28 [00:21<00:00, 1.31it/s]\n100%|██████████| 28/28 [00:21<00:00, 1.31it/s]\ntimestep: 197 max: 3.49 min: -3.63 mean: -0.01\n 0%| | 0/8 [00:00<?, ?it/s]\ntimestep: 169 max: 3.38 min: -3.52 mean: -0.01\n 12%|█▎ | 1/8 [00:00<00:04, 1.59it/s]\ntimestep: 141 max: 3.28 min: -3.42 mean: -0.01\n 25%|██▌ | 2/8 [00:01<00:03, 1.59it/s]\ntimestep: 113 max: 3.17 min: -3.33 mean: -0.01\n 38%|███▊ | 3/8 [00:01<00:03, 1.59it/s]\ntimestep: 85 max: 3.18 min: -3.28 mean: -0.01\n 50%|█████ | 4/8 [00:02<00:02, 1.59it/s]\ntimestep: 57 max: 3.2 min: -3.23 mean: -0.01\n 62%|██████▎ | 5/8 [00:03<00:01, 1.59it/s]\ntimestep: 29 max: 3.23 min: -3.14 mean: -0.02\n 75%|███████▌ | 6/8 [00:03<00:01, 1.59it/s]\ntimestep: 1 max: 3.23 min: -3.13mean: -0.02\n 88%|████████▊ | 7/8 [00:04<00:00, 1.59it/s]\n100%|██████████| 8/8 [00:05<00:00, 1.59it/s]\n100%|██████████| 8/8 [00:05<00:00, 1.59it/s]\nInference took: 30.549684524536133 3033", "metrics": { "predict_time": 30.936209, "total_time": 30.953206 }, "output": "https://replicate.delivery/pbxt/eJFb8u00UHymLyDZF88I1BPibfiOgL80erpua1wZVGh8D2zjA/image-3033-29.905627965927124.png", "started_at": "2023-11-19T12:23:59.504039Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/3zmjevtbpcawxhbkgsvosoz3fa", "cancel": "https://api.replicate.com/v1/predictions/3zmjevtbpcawxhbkgsvosoz3fa/cancel" }, "version": "a08504bd6b123bb993f648c6361041a3cc3f721a24ab6a1619b10f03dd8c0dff" }Generated inStarting fp16 torch.float32 cuda The current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported. Fused all loras in UNet Applied correction to prompts positive a woman redhead , dynamic walk, move, plane visible through windows, trending on cg society, digital art, a realistic girl, perfect slim body, realistic student, still from a live action movie, warm cinematic, sun rays, ray tracing, perfect perspective, promotional still, airport interior background,warm cinematic, sunset god rays, (full body)1.21, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 946 max: 4.06 min: -4.28 mean: -0.02 0%| | 0/28 [00:00<?, ?it/s] timestep: 919 max: 4.01 min: -4.31 mean: 0.01 4%|▎ | 1/28 [00:00<00:20, 1.31it/s] timestep: 892 max: 4.07 min: -4.24 mean: -0.03 7%|▋ | 2/28 [00:01<00:19, 1.31it/s] timestep: 865 max: 4.03 min: -4.27 mean: -0.0 11%|█ | 3/28 [00:02<00:19, 1.31it/s] timestep: 838 max: 4.05 min: -4.2 mean: -0.04 14%|█▍ | 4/28 [00:03<00:18, 1.31it/s] timestep: 811 max: 4.02 min: -4.21 mean: -0.02 18%|█▊ | 5/28 [00:03<00:17, 1.31it/s] timestep: 784 max: 4.01 min: -4.19 mean: -0.04 21%|██▏ | 6/28 [00:04<00:16, 1.31it/s] timestep: 757 max: 4.0 min: -4.19 mean: -0.03 25%|██▌ | 7/28 [00:05<00:16, 1.31it/s] timestep: 730 max: 3.96 min: -4.26 mean: -0.04 29%|██▊ | 8/28 [00:06<00:15, 1.31it/s] timestep: 703 max: 3.96 min: -4.27 mean: -0.03 32%|███▏ | 9/28 [00:06<00:14, 1.31it/s] timestep: 676 max: 3.95 min: -4.31 mean: -0.04 36%|███▌ | 10/28 [00:07<00:13, 1.31it/s] timestep: 649 max: 3.99 min: -4.31 mean: -0.04 39%|███▉ | 11/28 [00:08<00:13, 1.31it/s] timestep: 622 max: 4.01 min: -4.34 mean: -0.04 43%|████▎ | 12/28 [00:09<00:12, 1.31it/s] timestep: 595 max: 4.04 min: -4.34 mean: -0.04 46%|████▋ | 13/28 [00:09<00:11, 1.31it/s] timestep: 568 max: 4.05 min: -4.34 mean: -0.04 50%|█████ | 14/28 [00:10<00:10, 1.31it/s] timestep: 541 max: 4.06 min: -4.32 mean: -0.04 54%|█████▎ | 15/28 [00:11<00:09, 1.31it/s] timestep: 514 max: 4.06 min: -4.3 mean: -0.04 57%|█████▋ | 16/28 [00:12<00:09, 1.30it/s] timestep: 487 max: 4.06 min: -4.28 mean: -0.04 61%|██████ | 17/28 [00:13<00:08, 1.31it/s] timestep: 460 max: 4.04 min: -4.24mean: -0.04 64%|██████▍ | 18/28 [00:13<00:07, 1.31it/s] timestep: 433 max: 4.03 min: -4.19 mean: -0.03 68%|██████▊ | 19/28 [00:14<00:06, 1.31it/s] timestep: 406 max: 4.0 min: -4.13 mean: -0.03 71%|███████▏ | 20/28 [00:15<00:06, 1.31it/s] timestep: 379 max: 3.97 min: -4.06 mean: -0.03 75%|███████▌ | 21/28 [00:16<00:05, 1.31it/s] timestep: 352 max: 3.93 min: -3.98 mean: -0.03 79%|███████▊ | 22/28 [00:16<00:04, 1.31it/s] timestep: 325 max: 3.88 min: -3.89 mean: -0.02 82%|████████▏ | 23/28 [00:17<00:03, 1.31it/s] timestep: 298 max: 3.83 min: -3.82 mean: -0.02 86%|████████▌ | 24/28 [00:18<00:03, 1.31it/s] timestep: 271 max: 3.76 min: -3.8 mean: -0.02 89%|████████▉ | 25/28 [00:19<00:02, 1.31it/s] timestep: 244 max: 3.69 min: -3.78 mean: -0.01 93%|█████████▎| 26/28 [00:19<00:01, 1.31it/s] timestep: 217 max: 3.61 min: -3.75 mean: -0.01 96%|█████████▋| 27/28 [00:20<00:00, 1.31it/s] 100%|██████████| 28/28 [00:21<00:00, 1.31it/s] 100%|██████████| 28/28 [00:21<00:00, 1.31it/s] timestep: 197 max: 3.49 min: -3.63 mean: -0.01 0%| | 0/8 [00:00<?, ?it/s] timestep: 169 max: 3.38 min: -3.52 mean: -0.01 12%|█▎ | 1/8 [00:00<00:04, 1.59it/s] timestep: 141 max: 3.28 min: -3.42 mean: -0.01 25%|██▌ | 2/8 [00:01<00:03, 1.59it/s] timestep: 113 max: 3.17 min: -3.33 mean: -0.01 38%|███▊ | 3/8 [00:01<00:03, 1.59it/s] timestep: 85 max: 3.18 min: -3.28 mean: -0.01 50%|█████ | 4/8 [00:02<00:02, 1.59it/s] timestep: 57 max: 3.2 min: -3.23 mean: -0.01 62%|██████▎ | 5/8 [00:03<00:01, 1.59it/s] timestep: 29 max: 3.23 min: -3.14 mean: -0.02 75%|███████▌ | 6/8 [00:03<00:01, 1.59it/s] timestep: 1 max: 3.23 min: -3.13mean: -0.02 88%|████████▊ | 7/8 [00:04<00:00, 1.59it/s] 100%|██████████| 8/8 [00:05<00:00, 1.59it/s] 100%|██████████| 8/8 [00:05<00:00, 1.59it/s] Inference took: 30.549684524536133 3033Prediction
alexgenovese/sdxl-custom-model:ecde520aIDfcg77xtbxdkjubuxqtnrwasvzuStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays ((full body))
- refiner
- true
- denoising
- 0.8
- seed_number
- 12345
- guidance_scale
- 10
- negative_prompt
- num_inference_steps
- 35
{ "width": 1024, "height": 1024, "prompt": "a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays ((full body))", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays ((full body))", guidance_scale: 10, negative_prompt: "", num_inference_steps: 35 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays ((full body))", "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays ((full body))", "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays ((full body))"' \ -i 'guidance_scale=10' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=35'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays ((full body))", "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-19T12:25:41.657415Z", "created_at": "2023-11-19T12:25:10.975920Z", "data_removed": false, "error": null, "id": "fcg77xtbxdkjubuxqtnrwasvzu", "input": { "width": 1024, "height": 1024, "prompt": "a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays ((full body))", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 10, "negative_prompt": "", "num_inference_steps": 35 }, "logs": "Starting fp16 torch.float32 cuda\nThe current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported.\nFused all loras in UNet\nApplied correction to prompts positive a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays (full body)1.21, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 946 max: 4.06 min: -4.28 mean: -0.03\n 0%| | 0/28 [00:00<?, ?it/s]\ntimestep: 919 max: 3.99 min: -4.29 mean: -0.0\n 4%|▎ | 1/28 [00:00<00:20, 1.31it/s]\ntimestep: 892 max: 4.09 min: -4.23 mean: -0.04\n 7%|▋ | 2/28 [00:01<00:19, 1.31it/s]\ntimestep: 865 max: 4.04 min: -4.29 mean: -0.01\n 11%|█ | 3/28 [00:02<00:19, 1.31it/s]\ntimestep: 838 max: 4.11 min: -4.19 mean: -0.04\n 14%|█▍ | 4/28 [00:03<00:18, 1.31it/s]\ntimestep: 811 max: 4.05 min: -4.27 mean: -0.03\n 18%|█▊ | 5/28 [00:03<00:17, 1.31it/s]\ntimestep: 784 max: 4.07 min: -4.21 mean: -0.04\n 21%|██▏ | 6/28 [00:04<00:16, 1.31it/s]\ntimestep: 757 max: 4.03 min: -4.26 mean: -0.03\n 25%|██▌ | 7/28 [00:05<00:16, 1.31it/s]\ntimestep: 730 max: 4.03 min: -4.22 mean: -0.05\n 29%|██▊ | 8/28 [00:06<00:15, 1.31it/s]\ntimestep: 703 max: 4.0 min: -4.25 mean: -0.04\n 32%|███▏ | 9/28 [00:06<00:14, 1.31it/s]\ntimestep: 676 max: 3.97 min: -4.22 mean: -0.05\n 36%|███▌ | 10/28 [00:07<00:13, 1.31it/s]\ntimestep: 649 max: 3.92 min: -4.23 mean: -0.04\n 39%|███▉ | 11/28 [00:08<00:12, 1.31it/s]\ntimestep: 622 max: 3.89 min: -4.19 mean: -0.05\n 43%|████▎ | 12/28 [00:09<00:12, 1.31it/s]\ntimestep: 595 max: 3.82 min: -4.18 mean: -0.05\n 46%|████▋ | 13/28 [00:09<00:11, 1.31it/s]\ntimestep: 568 max: 3.77 min: -4.14 mean: -0.05\n 50%|█████ | 14/28 [00:10<00:10, 1.31it/s]\ntimestep: 541 max: 3.71 min: -4.12 mean: -0.06\n 54%|█████▎ | 15/28 [00:11<00:09, 1.31it/s]\ntimestep: 514 max: 3.66 min: -4.12 mean: -0.06\n 57%|█████▋ | 16/28 [00:12<00:09, 1.31it/s]\ntimestep: 487 max: 3.63 min: -4.1 mean: -0.07\n 61%|██████ | 17/28 [00:12<00:08, 1.31it/s]\ntimestep: 460 max: 3.6 min: -4.08 mean: -0.07\n 64%|██████▍ | 18/28 [00:13<00:07, 1.31it/s]\ntimestep: 433 max: 3.56 min: -4.04 mean: -0.08\n 68%|██████▊ | 19/28 [00:14<00:06, 1.30it/s]\ntimestep: 406 max: 3.53 min: -4.01 mean: -0.08\n 71%|███████▏ | 20/28 [00:15<00:06, 1.31it/s]\ntimestep: 379 max: 3.48 min: -3.97 mean: -0.08\n 75%|███████▌ | 21/28 [00:16<00:05, 1.31it/s]\ntimestep: 352 max: 3.43 min: -3.94 mean: -0.09\n 79%|███████▊ | 22/28 [00:16<00:04, 1.31it/s]\ntimestep: 325 max: 3.37 min: -3.9 mean: -0.09\n 82%|████████▏ | 23/28 [00:17<00:03, 1.31it/s]\ntimestep: 298 max: 3.34 min: -3.85 mean: -0.09\n 86%|████████▌ | 24/28 [00:18<00:03, 1.31it/s]\ntimestep: 271 max: 3.31 min: -3.8 mean: -0.09\n 89%|████████▉ | 25/28 [00:19<00:02, 1.31it/s]\ntimestep: 244 max: 3.26 min: -3.75 mean: -0.09\n 93%|█████████▎| 26/28 [00:19<00:01, 1.31it/s]\ntimestep: 217 max: 3.21 min: -3.71 mean: -0.09\n 96%|█████████▋| 27/28 [00:20<00:00, 1.31it/s]\n100%|██████████| 28/28 [00:21<00:00, 1.31it/s]\n100%|██████████| 28/28 [00:21<00:00, 1.31it/s]\ntimestep: 197 max: 3.06 min: -3.54 mean: -0.1\n 0%| | 0/8 [00:00<?, ?it/s]\ntimestep: 169 max: 2.91 min: -3.39 mean: -0.1\n 12%|█▎ | 1/8 [00:00<00:04, 1.59it/s]\ntimestep: 141 max: 2.77 min: -3.24 mean: -0.1\n 25%|██▌ | 2/8 [00:01<00:03, 1.59it/s]\ntimestep: 113 max: 2.71 min: -3.1 mean: -0.1\n 38%|███▊ | 3/8 [00:01<00:03, 1.59it/s]\ntimestep: 85 max: 2.72 min: -2.96 mean: -0.1\n 50%|█████ | 4/8 [00:02<00:02, 1.59it/s]\ntimestep: 57 max: 2.74 min: -2.81 mean: -0.1\n 62%|██████▎ | 5/8 [00:03<00:01, 1.59it/s]\ntimestep: 29 max: 2.69 min: -2.56 mean: -0.1\n 75%|███████▌ | 6/8 [00:03<00:01, 1.59it/s]\ntimestep: 1 max: 2.69 min: -2.55 mean: -0.1\n 88%|████████▊ | 7/8 [00:04<00:00, 1.59it/s]\n100%|██████████| 8/8 [00:05<00:00, 1.59it/s]\n100%|██████████| 8/8 [00:05<00:00, 1.59it/s]\nInference took: 30.28657102584839 23116", "metrics": { "predict_time": 30.669675, "total_time": 30.681495 }, "output": "https://replicate.delivery/pbxt/r0G0oJgGgtJPLFePsAPB7bkYDy9IUgPi7RYNzfO9iXUFD75RA/image-23116-29.72296905517578.png", "started_at": "2023-11-19T12:25:10.987740Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/fcg77xtbxdkjubuxqtnrwasvzu", "cancel": "https://api.replicate.com/v1/predictions/fcg77xtbxdkjubuxqtnrwasvzu/cancel" }, "version": "a08504bd6b123bb993f648c6361041a3cc3f721a24ab6a1619b10f03dd8c0dff" }Generated inStarting fp16 torch.float32 cuda The current API is supported for operating with a single LoRA file. You are trying to load and fuse more than one LoRA which is not well-supported. Fused all loras in UNet Applied correction to prompts positive a woman redhead, dynamic walk, plane visible through windows, perfect slim body, warm cinematic, sun rays (full body)1.21, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 946 max: 4.06 min: -4.28 mean: -0.03 0%| | 0/28 [00:00<?, ?it/s] timestep: 919 max: 3.99 min: -4.29 mean: -0.0 4%|▎ | 1/28 [00:00<00:20, 1.31it/s] timestep: 892 max: 4.09 min: -4.23 mean: -0.04 7%|▋ | 2/28 [00:01<00:19, 1.31it/s] timestep: 865 max: 4.04 min: -4.29 mean: -0.01 11%|█ | 3/28 [00:02<00:19, 1.31it/s] timestep: 838 max: 4.11 min: -4.19 mean: -0.04 14%|█▍ | 4/28 [00:03<00:18, 1.31it/s] timestep: 811 max: 4.05 min: -4.27 mean: -0.03 18%|█▊ | 5/28 [00:03<00:17, 1.31it/s] timestep: 784 max: 4.07 min: -4.21 mean: -0.04 21%|██▏ | 6/28 [00:04<00:16, 1.31it/s] timestep: 757 max: 4.03 min: -4.26 mean: -0.03 25%|██▌ | 7/28 [00:05<00:16, 1.31it/s] timestep: 730 max: 4.03 min: -4.22 mean: -0.05 29%|██▊ | 8/28 [00:06<00:15, 1.31it/s] timestep: 703 max: 4.0 min: -4.25 mean: -0.04 32%|███▏ | 9/28 [00:06<00:14, 1.31it/s] timestep: 676 max: 3.97 min: -4.22 mean: -0.05 36%|███▌ | 10/28 [00:07<00:13, 1.31it/s] timestep: 649 max: 3.92 min: -4.23 mean: -0.04 39%|███▉ | 11/28 [00:08<00:12, 1.31it/s] timestep: 622 max: 3.89 min: -4.19 mean: -0.05 43%|████▎ | 12/28 [00:09<00:12, 1.31it/s] timestep: 595 max: 3.82 min: -4.18 mean: -0.05 46%|████▋ | 13/28 [00:09<00:11, 1.31it/s] timestep: 568 max: 3.77 min: -4.14 mean: -0.05 50%|█████ | 14/28 [00:10<00:10, 1.31it/s] timestep: 541 max: 3.71 min: -4.12 mean: -0.06 54%|█████▎ | 15/28 [00:11<00:09, 1.31it/s] timestep: 514 max: 3.66 min: -4.12 mean: -0.06 57%|█████▋ | 16/28 [00:12<00:09, 1.31it/s] timestep: 487 max: 3.63 min: -4.1 mean: -0.07 61%|██████ | 17/28 [00:12<00:08, 1.31it/s] timestep: 460 max: 3.6 min: -4.08 mean: -0.07 64%|██████▍ | 18/28 [00:13<00:07, 1.31it/s] timestep: 433 max: 3.56 min: -4.04 mean: -0.08 68%|██████▊ | 19/28 [00:14<00:06, 1.30it/s] timestep: 406 max: 3.53 min: -4.01 mean: -0.08 71%|███████▏ | 20/28 [00:15<00:06, 1.31it/s] timestep: 379 max: 3.48 min: -3.97 mean: -0.08 75%|███████▌ | 21/28 [00:16<00:05, 1.31it/s] timestep: 352 max: 3.43 min: -3.94 mean: -0.09 79%|███████▊ | 22/28 [00:16<00:04, 1.31it/s] timestep: 325 max: 3.37 min: -3.9 mean: -0.09 82%|████████▏ | 23/28 [00:17<00:03, 1.31it/s] timestep: 298 max: 3.34 min: -3.85 mean: -0.09 86%|████████▌ | 24/28 [00:18<00:03, 1.31it/s] timestep: 271 max: 3.31 min: -3.8 mean: -0.09 89%|████████▉ | 25/28 [00:19<00:02, 1.31it/s] timestep: 244 max: 3.26 min: -3.75 mean: -0.09 93%|█████████▎| 26/28 [00:19<00:01, 1.31it/s] timestep: 217 max: 3.21 min: -3.71 mean: -0.09 96%|█████████▋| 27/28 [00:20<00:00, 1.31it/s] 100%|██████████| 28/28 [00:21<00:00, 1.31it/s] 100%|██████████| 28/28 [00:21<00:00, 1.31it/s] timestep: 197 max: 3.06 min: -3.54 mean: -0.1 0%| | 0/8 [00:00<?, ?it/s] timestep: 169 max: 2.91 min: -3.39 mean: -0.1 12%|█▎ | 1/8 [00:00<00:04, 1.59it/s] timestep: 141 max: 2.77 min: -3.24 mean: -0.1 25%|██▌ | 2/8 [00:01<00:03, 1.59it/s] timestep: 113 max: 2.71 min: -3.1 mean: -0.1 38%|███▊ | 3/8 [00:01<00:03, 1.59it/s] timestep: 85 max: 2.72 min: -2.96 mean: -0.1 50%|█████ | 4/8 [00:02<00:02, 1.59it/s] timestep: 57 max: 2.74 min: -2.81 mean: -0.1 62%|██████▎ | 5/8 [00:03<00:01, 1.59it/s] timestep: 29 max: 2.69 min: -2.56 mean: -0.1 75%|███████▌ | 6/8 [00:03<00:01, 1.59it/s] timestep: 1 max: 2.69 min: -2.55 mean: -0.1 88%|████████▊ | 7/8 [00:04<00:00, 1.59it/s] 100%|██████████| 8/8 [00:05<00:00, 1.59it/s] 100%|██████████| 8/8 [00:05<00:00, 1.59it/s] Inference took: 30.28657102584839 23116Prediction
alexgenovese/sdxl-custom-model:ecde520aIDs4qcoadbcpvjfzxn5ooz2ncvmmStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))
- refiner
- true
- denoising
- 0.8
- seed_number
- 12345
- guidance_scale
- 8
- negative_prompt
- num_inference_steps
- 35
{ "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 8, "negative_prompt": "", "num_inference_steps": 35 }npm install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", { input: { width: 1024, height: 1024, prompt: "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", guidance_scale: 8, negative_prompt: "", num_inference_steps: 35 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateSet theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the clientimport replicateRun alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "alexgenovese/sdxl-custom-model:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", input={ "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "guidance_scale": 8, "negative_prompt": "", "num_inference_steps": 35 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run alexgenovese/sdxl-custom-model using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3", "input": { "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "guidance_scale": 8, "negative_prompt": "", "num_inference_steps": 35 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cogIf you don’t have Homebrew, there are other installation options available.
Pull and run alexgenovese/sdxl-custom-model using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))"' \ -i 'guidance_scale=8' \ -i 'negative_prompt=""' \ -i 'num_inference_steps=35'To learn more, take a look at the Cog documentation.
Pull and run alexgenovese/sdxl-custom-model using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/alexgenovese/sdxl-custom-model@sha256:ecde520a01119812673bb13aca08e4856ff2708829a48bc036a87bf722cc4ae3curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "guidance_scale": 8, "negative_prompt": "", "num_inference_steps": 35 } }' \ http://localhost:5000/predictionsOutput
{ "completed_at": "2023-11-19T17:34:10.960801Z", "created_at": "2023-11-19T17:32:32.129311Z", "data_removed": false, "error": null, "id": "s4qcoadbcpvjfzxn5ooz2ncvmm", "input": { "width": 1024, "height": 1024, "prompt": "a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, ((full body)), ((3/4 view))", "refiner": true, "denoising": 0.8, "seed_number": 12345, "guidance_scale": 8, "negative_prompt": "", "num_inference_steps": 35 }, "logs": "Starting fp16 torch.float16 cuda\nFused all loras in UNet\nApplied correction to prompts positive a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, (full body)1.21, (3/4 view)1.21, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30\nApplied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6\nApplied optimization\nCreated compel for prompts\nStarting inference...\ntimestep: 946 max: 3.88 min: -3.88 mean: -0.02\n 0%| | 0/28 [00:00<?, ?it/s]\ntimestep: 919 max: 3.93 min: -3.91 mean: -0.02\n 4%|▎ | 1/28 [00:00<00:20, 1.33it/s]\ntimestep: 892 max: 3.92 min: -3.96 mean: -0.03\n 7%|▋ | 2/28 [00:00<00:10, 2.45it/s]\ntimestep: 865 max: 3.98 min: -3.98 mean: -0.04\n 11%|█ | 3/28 [00:01<00:10, 2.35it/s]\ntimestep: 838 max: 3.9 min: -3.99 mean: -0.04\n 14%|█▍ | 4/28 [00:01<00:07, 3.08it/s]\ntimestep: 811 max: 4.04 min: -4.0 mean: -0.05\n 18%|█▊ | 5/28 [00:01<00:06, 3.73it/s]\ntimestep: 784 max: 4.05 min: -3.98 mean: -0.05\n 21%|██▏ | 6/28 [00:01<00:05, 4.27it/s]\ntimestep: 757 max: 4.08 min: -3.95 mean: -0.06\n 25%|██▌ | 7/28 [00:02<00:04, 4.71it/s]\ntimestep: 730 max: 4.09 min: -3.95mean: -0.06\n 29%|██▊ | 8/28 [00:02<00:03, 5.05it/s]\ntimestep: 703 max: 4.12 min: -3.97 mean:-0.07\n 32%|███▏ | 9/28 [00:02<00:03, 5.31it/s]\ntimestep: 676 max: 4.15 min: -4.01 mean: -0.07\n 36%|███▌ | 10/28 [00:02<00:03, 5.50it/s]\ntimestep: 649 max: 4.18 min: -4.05 mean: -0.08\n 39%|███▉ | 11/28 [00:02<00:03, 5.64it/s]\ntimestep: 622 max: 4.22 min: -4.08 mean: -0.09\n 43%|████▎ | 12/28 [00:02<00:02, 5.74it/s]\ntimestep: 595 max: 4.25 min: -4.11 mean: -0.09\n 46%|████▋ | 13/28 [00:03<00:02, 5.81it/s]\ntimestep: 568 max: 4.28 min: -4.14 mean: -0.1\n 50%|█████ | 14/28 [00:03<00:02, 5.86it/s]\ntimestep: 541 max: 4.3 min: -4.17 mean: -0.1\n 54%|█████▎ | 15/28 [00:03<00:02, 5.90it/s]\ntimestep: 514 max: 4.32 min: -4.19 mean: -0.11\n 57%|█████▋ | 16/28 [00:03<00:02, 5.92it/s]\ntimestep: 487 max: 4.34 min: -4.2 mean: -0.11\n 61%|██████ | 17/28 [00:03<00:01, 5.93it/s]\ntimestep: 460 max: 4.35 min: -4.2 mean: -0.12\n 64%|██████▍ | 18/28 [00:03<00:01, 5.95it/s]\ntimestep: 433 max: 4.35 min: -4.2 mean: -0.13\n 68%|██████▊ | 19/28 [00:04<00:01, 5.95it/s]\ntimestep: 406 max: 4.35 min: -4.18 mean: -0.13\n 71%|███████▏ | 20/28 [00:04<00:01, 5.96it/s]\ntimestep: 379 max: 4.34 min: -4.16 mean: -0.14\n 75%|███████▌ | 21/28 [00:04<00:01, 5.97it/s]\ntimestep: 352 max: 4.31 min: -4.13 mean: -0.14\n 79%|███████▊ | 22/28 [00:04<00:01, 5.97it/s]\ntimestep: 325 max: 4.28 min: -4.09 mean: -0.14\n 82%|████████▏ | 23/28 [00:04<00:00, 5.97it/s]\ntimestep: 298 max: 4.24 min: -4.04 mean: -0.15\n 86%|████████▌ | 24/28 [00:04<00:00, 5.97it/s]\ntimestep: 271 max: 4.19 min: -3.98 mean: -0.15\n 89%|████████▉ | 25/28 [00:05<00:00, 5.97it/s]\ntimestep: 244 max: 4.13 min: -3.9 mean: -0.15\n 93%|█████████▎| 26/28 [00:05<00:00, 5.97it/s]\ntimestep: 217 max: 4.06 min: -3.81 mean: -0.16\n 96%|█████████▋| 27/28 [00:05<00:00, 5.96it/s]\n100%|██████████| 28/28 [00:05<00:00, 5.96it/s]\n100%|██████████| 28/28 [00:05<00:00, 5.04it/s]\ntimestep: 197 max: 3.91 min: -3.68 mean: -0.16\n 0%| | 0/8 [00:00<?, ?it/s]\ntimestep: 169 max: 3.78 min: -3.56 mean: -0.16\n 12%|█▎ | 1/8 [00:00<00:01, 6.93it/s]\ntimestep: 141 max: 3.66 min: -3.45 mean: -0.16\n 25%|██▌ | 2/8 [00:00<00:00, 7.26it/s]\ntimestep: 113 max: 3.54 min: -3.33 mean: -0.16\n 38%|███▊ | 3/8 [00:00<00:00, 7.35it/s]\ntimestep: 85 max: 3.43 min: -3.21 mean: -0.16\n 50%|█████ | 4/8 [00:00<00:00, 7.41it/s]\ntimestep: 57 max: 3.3 min: -3.11 mean: -0.16\n 62%|██████▎ | 5/8 [00:00<00:00, 7.43it/s]\ntimestep: 29 max: 3.1 min: -3.05 mean: -0.16\n 75%|███████▌ | 6/8 [00:00<00:00, 7.45it/s]\ntimestep: 1 max: 3.05 min: -3.04 mean: -0.16\n 88%|████████▊ | 7/8 [00:00<00:00, 7.47it/s]\n100%|██████████| 8/8 [00:01<00:00, 7.47it/s]\n100%|██████████| 8/8 [00:01<00:00, 7.41it/s]\nInference took: 12.205230474472046 63072", "metrics": { "predict_time": 12.558845, "total_time": 98.83149 }, "output": "https://replicate.delivery/pbxt/Lo5hT6YxQWZXJFkWU654WqrCGFA092DwcLiR27fpikeSkfzjA/image-63072-11.602858304977417.png", "started_at": "2023-11-19T17:33:58.401956Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/s4qcoadbcpvjfzxn5ooz2ncvmm", "cancel": "https://api.replicate.com/v1/predictions/s4qcoadbcpvjfzxn5ooz2ncvmm/cancel" }, "version": "3515432583322954b49cfddcb9dcb200f5a5665d75f73b2def6e771db791ee5a" }Generated inStarting fp16 torch.float16 cuda Fused all loras in UNet Applied correction to prompts positive a full body realistic photo of beautiful woman 40 y.o, walking in Madison Square Garden, smile, blue eyes, short hair, dark makeup, hyperdetailed photography, soft light, (full body)1.21, (3/4 view)1.21, detailed eyes, (masterpiece,best quality,ultra_detailed,highres,absurdres)1.20, 4k, professional, intricate details even to the smallest particle, extreme detail of the environment, sharp portrait, well lit, (ultra realistic, realistic)1.90, beautiful shadows, bright, photo quality, masterpiece, 8k, ultra-detailed, highly detailed, sharp focus, award winning, octane render unreal engine, volumetrics dtx, high definition, bokeh, (fashion model)1.50, (realistic, photorealistic)2.00, (fashion-forward)1.30 Applied correction to negative prompts ,(worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art)1.40, (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name)1.20, (blur, blurry, grainy)1.10, morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur)1.30, (3D ,3D Game, 3D Game Scene, 3D Character)1.10, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities)1.30, peopleneg, unaestheticXL_Jug6 Applied optimization Created compel for prompts Starting inference... timestep: 946 max: 3.88 min: -3.88 mean: -0.02 0%| | 0/28 [00:00<?, ?it/s] timestep: 919 max: 3.93 min: -3.91 mean: -0.02 4%|▎ | 1/28 [00:00<00:20, 1.33it/s] timestep: 892 max: 3.92 min: -3.96 mean: -0.03 7%|▋ | 2/28 [00:00<00:10, 2.45it/s] timestep: 865 max: 3.98 min: -3.98 mean: -0.04 11%|█ | 3/28 [00:01<00:10, 2.35it/s] timestep: 838 max: 3.9 min: -3.99 mean: -0.04 14%|█▍ | 4/28 [00:01<00:07, 3.08it/s] timestep: 811 max: 4.04 min: -4.0 mean: -0.05 18%|█▊ | 5/28 [00:01<00:06, 3.73it/s] timestep: 784 max: 4.05 min: -3.98 mean: -0.05 21%|██▏ | 6/28 [00:01<00:05, 4.27it/s] timestep: 757 max: 4.08 min: -3.95 mean: -0.06 25%|██▌ | 7/28 [00:02<00:04, 4.71it/s] timestep: 730 max: 4.09 min: -3.95mean: -0.06 29%|██▊ | 8/28 [00:02<00:03, 5.05it/s] timestep: 703 max: 4.12 min: -3.97 mean:-0.07 32%|███▏ | 9/28 [00:02<00:03, 5.31it/s] timestep: 676 max: 4.15 min: -4.01 mean: -0.07 36%|███▌ | 10/28 [00:02<00:03, 5.50it/s] timestep: 649 max: 4.18 min: -4.05 mean: -0.08 39%|███▉ | 11/28 [00:02<00:03, 5.64it/s] timestep: 622 max: 4.22 min: -4.08 mean: -0.09 43%|████▎ | 12/28 [00:02<00:02, 5.74it/s] timestep: 595 max: 4.25 min: -4.11 mean: -0.09 46%|████▋ | 13/28 [00:03<00:02, 5.81it/s] timestep: 568 max: 4.28 min: -4.14 mean: -0.1 50%|█████ | 14/28 [00:03<00:02, 5.86it/s] timestep: 541 max: 4.3 min: -4.17 mean: -0.1 54%|█████▎ | 15/28 [00:03<00:02, 5.90it/s] timestep: 514 max: 4.32 min: -4.19 mean: -0.11 57%|█████▋ | 16/28 [00:03<00:02, 5.92it/s] timestep: 487 max: 4.34 min: -4.2 mean: -0.11 61%|██████ | 17/28 [00:03<00:01, 5.93it/s] timestep: 460 max: 4.35 min: -4.2 mean: -0.12 64%|██████▍ | 18/28 [00:03<00:01, 5.95it/s] timestep: 433 max: 4.35 min: -4.2 mean: -0.13 68%|██████▊ | 19/28 [00:04<00:01, 5.95it/s] timestep: 406 max: 4.35 min: -4.18 mean: -0.13 71%|███████▏ | 20/28 [00:04<00:01, 5.96it/s] timestep: 379 max: 4.34 min: -4.16 mean: -0.14 75%|███████▌ | 21/28 [00:04<00:01, 5.97it/s] timestep: 352 max: 4.31 min: -4.13 mean: -0.14 79%|███████▊ | 22/28 [00:04<00:01, 5.97it/s] timestep: 325 max: 4.28 min: -4.09 mean: -0.14 82%|████████▏ | 23/28 [00:04<00:00, 5.97it/s] timestep: 298 max: 4.24 min: -4.04 mean: -0.15 86%|████████▌ | 24/28 [00:04<00:00, 5.97it/s] timestep: 271 max: 4.19 min: -3.98 mean: -0.15 89%|████████▉ | 25/28 [00:05<00:00, 5.97it/s] timestep: 244 max: 4.13 min: -3.9 mean: -0.15 93%|█████████▎| 26/28 [00:05<00:00, 5.97it/s] timestep: 217 max: 4.06 min: -3.81 mean: -0.16 96%|█████████▋| 27/28 [00:05<00:00, 5.96it/s] 100%|██████████| 28/28 [00:05<00:00, 5.96it/s] 100%|██████████| 28/28 [00:05<00:00, 5.04it/s] timestep: 197 max: 3.91 min: -3.68 mean: -0.16 0%| | 0/8 [00:00<?, ?it/s] timestep: 169 max: 3.78 min: -3.56 mean: -0.16 12%|█▎ | 1/8 [00:00<00:01, 6.93it/s] timestep: 141 max: 3.66 min: -3.45 mean: -0.16 25%|██▌ | 2/8 [00:00<00:00, 7.26it/s] timestep: 113 max: 3.54 min: -3.33 mean: -0.16 38%|███▊ | 3/8 [00:00<00:00, 7.35it/s] timestep: 85 max: 3.43 min: -3.21 mean: -0.16 50%|█████ | 4/8 [00:00<00:00, 7.41it/s] timestep: 57 max: 3.3 min: -3.11 mean: -0.16 62%|██████▎ | 5/8 [00:00<00:00, 7.43it/s] timestep: 29 max: 3.1 min: -3.05 mean: -0.16 75%|███████▌ | 6/8 [00:00<00:00, 7.45it/s] timestep: 1 max: 3.05 min: -3.04 mean: -0.16 88%|████████▊ | 7/8 [00:00<00:00, 7.47it/s] 100%|██████████| 8/8 [00:01<00:00, 7.47it/s] 100%|██████████| 8/8 [00:01<00:00, 7.41it/s] Inference took: 12.205230474472046 63072
Want to make some of these yourself?
Run this model