fofr
/
sdxl-cross-section
SDXL fine-tune based on illustrated cross sections
- Public
- 1.2K runs
-
L40S
Prediction
fofr/sdxl-cross-section:26d3c19fIDrqwk7j3bynt72tq6jbu4ipfrpqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedby @cbh123Input
- width
- 1600
- height
- 1024
- prompt
- A cross section TOK of a planet
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1600, "height": 1024, "prompt": "A cross section TOK of a planet", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-cross-section using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-cross-section:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", { input: { width: 1600, height: 1024, prompt: "A cross section TOK of a planet", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, prompt_strength: 0.8, num_inference_steps: 50 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun fofr/sdxl-cross-section using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-cross-section:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", input={ "width": 1600, "height": 1024, "prompt": "A cross section TOK of a planet", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run fofr/sdxl-cross-section 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": "26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", "input": { "width": 1600, "height": 1024, "prompt": "A cross section TOK of a planet", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/fofr/sdxl-cross-section@sha256:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d \ -i 'width=1600' \ -i 'height=1024' \ -i 'prompt="A cross section TOK of a planet"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/fofr/sdxl-cross-section@sha256:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1dcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1600, "height": 1024, "prompt": "A cross section TOK of a planet", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-08-21T15:06:05.484598Z", "created_at": "2023-08-21T15:05:40.738654Z", "data_removed": false, "error": null, "id": "rqwk7j3bynt72tq6jbu4ipfrpq", "input": { "width": 1600, "height": 1024, "prompt": "A cross section TOK of a planet", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 5971\nPrompt: A cross section <s0><s1> of a planet\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:21, 2.29it/s]\n 4%|▍ | 2/50 [00:00<00:21, 2.28it/s]\n 6%|▌ | 3/50 [00:01<00:20, 2.28it/s]\n 8%|▊ | 4/50 [00:01<00:20, 2.28it/s]\n 10%|█ | 5/50 [00:02<00:19, 2.27it/s]\n 12%|█▏ | 6/50 [00:02<00:19, 2.27it/s]\n 14%|█▍ | 7/50 [00:03<00:18, 2.27it/s]\n 16%|█▌ | 8/50 [00:03<00:18, 2.27it/s]\n 18%|█▊ | 9/50 [00:03<00:18, 2.27it/s]\n 20%|██ | 10/50 [00:04<00:17, 2.27it/s]\n 22%|██▏ | 11/50 [00:04<00:17, 2.27it/s]\n 24%|██▍ | 12/50 [00:05<00:16, 2.27it/s]\n 26%|██▌ | 13/50 [00:05<00:16, 2.27it/s]\n 28%|██▊ | 14/50 [00:06<00:15, 2.26it/s]\n 30%|███ | 15/50 [00:06<00:15, 2.26it/s]\n 32%|███▏ | 16/50 [00:07<00:15, 2.26it/s]\n 34%|███▍ | 17/50 [00:07<00:14, 2.26it/s]\n 36%|███▌ | 18/50 [00:07<00:14, 2.26it/s]\n 38%|███▊ | 19/50 [00:08<00:13, 2.26it/s]\n 40%|████ | 20/50 [00:08<00:13, 2.26it/s]\n 42%|████▏ | 21/50 [00:09<00:12, 2.26it/s]\n 44%|████▍ | 22/50 [00:09<00:12, 2.26it/s]\n 46%|████▌ | 23/50 [00:10<00:11, 2.26it/s]\n 48%|████▊ | 24/50 [00:10<00:11, 2.26it/s]\n 50%|█████ | 25/50 [00:11<00:11, 2.26it/s]\n 52%|█████▏ | 26/50 [00:11<00:10, 2.26it/s]\n 54%|█████▍ | 27/50 [00:11<00:10, 2.26it/s]\n 56%|█████▌ | 28/50 [00:12<00:09, 2.26it/s]\n 58%|█████▊ | 29/50 [00:12<00:09, 2.26it/s]\n 60%|██████ | 30/50 [00:13<00:08, 2.26it/s]\n 62%|██████▏ | 31/50 [00:13<00:08, 2.26it/s]\n 64%|██████▍ | 32/50 [00:14<00:07, 2.26it/s]\n 66%|██████▌ | 33/50 [00:14<00:07, 2.26it/s]\n 68%|██████▊ | 34/50 [00:15<00:07, 2.26it/s]\n 70%|███████ | 35/50 [00:15<00:06, 2.26it/s]\n 72%|███████▏ | 36/50 [00:15<00:06, 2.26it/s]\n 74%|███████▍ | 37/50 [00:16<00:05, 2.26it/s]\n 76%|███████▌ | 38/50 [00:16<00:05, 2.26it/s]\n 78%|███████▊ | 39/50 [00:17<00:04, 2.26it/s]\n 80%|████████ | 40/50 [00:17<00:04, 2.26it/s]\n 82%|████████▏ | 41/50 [00:18<00:03, 2.26it/s]\n 84%|████████▍ | 42/50 [00:18<00:03, 2.26it/s]\n 86%|████████▌ | 43/50 [00:19<00:03, 2.26it/s]\n 88%|████████▊ | 44/50 [00:19<00:02, 2.26it/s]\n 90%|█████████ | 45/50 [00:19<00:02, 2.26it/s]\n 92%|█████████▏| 46/50 [00:20<00:01, 2.26it/s]\n 94%|█████████▍| 47/50 [00:20<00:01, 2.26it/s]\n 96%|█████████▌| 48/50 [00:21<00:00, 2.26it/s]\n 98%|█████████▊| 49/50 [00:21<00:00, 2.26it/s]\n100%|██████████| 50/50 [00:22<00:00, 2.26it/s]\n100%|██████████| 50/50 [00:22<00:00, 2.26it/s]", "metrics": { "predict_time": 24.746316, "total_time": 24.745944 }, "output": [ "https://replicate.delivery/pbxt/meIgFQsxv2XOQ6wvzdDFRS4ndUPaKJXqob3CvKwRVqEueScRA/out-0.png" ], "started_at": "2023-08-21T15:05:40.738282Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rqwk7j3bynt72tq6jbu4ipfrpq", "cancel": "https://api.replicate.com/v1/predictions/rqwk7j3bynt72tq6jbu4ipfrpq/cancel" }, "version": "26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d" }Generated inUsing seed: 5971 Prompt: A cross section <s0><s1> of a planet txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:21, 2.29it/s] 4%|▍ | 2/50 [00:00<00:21, 2.28it/s] 6%|▌ | 3/50 [00:01<00:20, 2.28it/s] 8%|▊ | 4/50 [00:01<00:20, 2.28it/s] 10%|█ | 5/50 [00:02<00:19, 2.27it/s] 12%|█▏ | 6/50 [00:02<00:19, 2.27it/s] 14%|█▍ | 7/50 [00:03<00:18, 2.27it/s] 16%|█▌ | 8/50 [00:03<00:18, 2.27it/s] 18%|█▊ | 9/50 [00:03<00:18, 2.27it/s] 20%|██ | 10/50 [00:04<00:17, 2.27it/s] 22%|██▏ | 11/50 [00:04<00:17, 2.27it/s] 24%|██▍ | 12/50 [00:05<00:16, 2.27it/s] 26%|██▌ | 13/50 [00:05<00:16, 2.27it/s] 28%|██▊ | 14/50 [00:06<00:15, 2.26it/s] 30%|███ | 15/50 [00:06<00:15, 2.26it/s] 32%|███▏ | 16/50 [00:07<00:15, 2.26it/s] 34%|███▍ | 17/50 [00:07<00:14, 2.26it/s] 36%|███▌ | 18/50 [00:07<00:14, 2.26it/s] 38%|███▊ | 19/50 [00:08<00:13, 2.26it/s] 40%|████ | 20/50 [00:08<00:13, 2.26it/s] 42%|████▏ | 21/50 [00:09<00:12, 2.26it/s] 44%|████▍ | 22/50 [00:09<00:12, 2.26it/s] 46%|████▌ | 23/50 [00:10<00:11, 2.26it/s] 48%|████▊ | 24/50 [00:10<00:11, 2.26it/s] 50%|█████ | 25/50 [00:11<00:11, 2.26it/s] 52%|█████▏ | 26/50 [00:11<00:10, 2.26it/s] 54%|█████▍ | 27/50 [00:11<00:10, 2.26it/s] 56%|█████▌ | 28/50 [00:12<00:09, 2.26it/s] 58%|█████▊ | 29/50 [00:12<00:09, 2.26it/s] 60%|██████ | 30/50 [00:13<00:08, 2.26it/s] 62%|██████▏ | 31/50 [00:13<00:08, 2.26it/s] 64%|██████▍ | 32/50 [00:14<00:07, 2.26it/s] 66%|██████▌ | 33/50 [00:14<00:07, 2.26it/s] 68%|██████▊ | 34/50 [00:15<00:07, 2.26it/s] 70%|███████ | 35/50 [00:15<00:06, 2.26it/s] 72%|███████▏ | 36/50 [00:15<00:06, 2.26it/s] 74%|███████▍ | 37/50 [00:16<00:05, 2.26it/s] 76%|███████▌ | 38/50 [00:16<00:05, 2.26it/s] 78%|███████▊ | 39/50 [00:17<00:04, 2.26it/s] 80%|████████ | 40/50 [00:17<00:04, 2.26it/s] 82%|████████▏ | 41/50 [00:18<00:03, 2.26it/s] 84%|████████▍ | 42/50 [00:18<00:03, 2.26it/s] 86%|████████▌ | 43/50 [00:19<00:03, 2.26it/s] 88%|████████▊ | 44/50 [00:19<00:02, 2.26it/s] 90%|█████████ | 45/50 [00:19<00:02, 2.26it/s] 92%|█████████▏| 46/50 [00:20<00:01, 2.26it/s] 94%|█████████▍| 47/50 [00:20<00:01, 2.26it/s] 96%|█████████▌| 48/50 [00:21<00:00, 2.26it/s] 98%|█████████▊| 49/50 [00:21<00:00, 2.26it/s] 100%|██████████| 50/50 [00:22<00:00, 2.26it/s] 100%|██████████| 50/50 [00:22<00:00, 2.26it/s]Prediction
fofr/sdxl-cross-section:26d3c19fIDn3qghglb5eycp7rm5p5aiqjhtuStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A cross section TOK of an iphone
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "A cross section TOK of an iphone", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-cross-section using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-cross-section:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", { input: { width: 1024, height: 1024, prompt: "A cross section TOK of an iphone", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, prompt_strength: 0.8, num_inference_steps: 50 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun fofr/sdxl-cross-section using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-cross-section:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", input={ "width": 1024, "height": 1024, "prompt": "A cross section TOK of an iphone", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run fofr/sdxl-cross-section 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": "26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", "input": { "width": 1024, "height": 1024, "prompt": "A cross section TOK of an iphone", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/fofr/sdxl-cross-section@sha256:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A cross section TOK of an iphone"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/fofr/sdxl-cross-section@sha256:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1dcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A cross section TOK of an iphone", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-08-20T22:11:30.459796Z", "created_at": "2023-08-20T22:11:14.804911Z", "data_removed": false, "error": null, "id": "n3qghglb5eycp7rm5p5aiqjhtu", "input": { "width": 1024, "height": 1024, "prompt": "A cross section TOK of an iphone", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 64800\nPrompt: A cross section <s0><s1> of an iphone\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:13, 3.67it/s]\n 4%|▍ | 2/50 [00:00<00:13, 3.65it/s]\n 6%|▌ | 3/50 [00:00<00:12, 3.65it/s]\n 8%|▊ | 4/50 [00:01<00:12, 3.65it/s]\n 10%|█ | 5/50 [00:01<00:12, 3.66it/s]\n 12%|█▏ | 6/50 [00:01<00:12, 3.66it/s]\n 14%|█▍ | 7/50 [00:01<00:11, 3.66it/s]\n 16%|█▌ | 8/50 [00:02<00:11, 3.66it/s]\n 18%|█▊ | 9/50 [00:02<00:11, 3.66it/s]\n 20%|██ | 10/50 [00:02<00:10, 3.66it/s]\n 22%|██▏ | 11/50 [00:03<00:10, 3.65it/s]\n 24%|██▍ | 12/50 [00:03<00:10, 3.65it/s]\n 26%|██▌ | 13/50 [00:03<00:10, 3.65it/s]\n 28%|██▊ | 14/50 [00:03<00:09, 3.65it/s]\n 30%|███ | 15/50 [00:04<00:09, 3.65it/s]\n 32%|███▏ | 16/50 [00:04<00:09, 3.65it/s]\n 34%|███▍ | 17/50 [00:04<00:09, 3.65it/s]\n 36%|███▌ | 18/50 [00:04<00:08, 3.65it/s]\n 38%|███▊ | 19/50 [00:05<00:08, 3.65it/s]\n 40%|████ | 20/50 [00:05<00:08, 3.65it/s]\n 42%|████▏ | 21/50 [00:05<00:07, 3.65it/s]\n 44%|████▍ | 22/50 [00:06<00:07, 3.65it/s]\n 46%|████▌ | 23/50 [00:06<00:07, 3.65it/s]\n 48%|████▊ | 24/50 [00:06<00:07, 3.65it/s]\n 50%|█████ | 25/50 [00:06<00:06, 3.65it/s]\n 52%|█████▏ | 26/50 [00:07<00:06, 3.65it/s]\n 54%|█████▍ | 27/50 [00:07<00:06, 3.65it/s]\n 56%|█████▌ | 28/50 [00:07<00:06, 3.65it/s]\n 58%|█████▊ | 29/50 [00:07<00:05, 3.65it/s]\n 60%|██████ | 30/50 [00:08<00:05, 3.64it/s]\n 62%|██████▏ | 31/50 [00:08<00:05, 3.64it/s]\n 64%|██████▍ | 32/50 [00:08<00:04, 3.64it/s]\n 66%|██████▌ | 33/50 [00:09<00:04, 3.64it/s]\n 68%|██████▊ | 34/50 [00:09<00:04, 3.64it/s]\n 70%|███████ | 35/50 [00:09<00:04, 3.64it/s]\n 72%|███████▏ | 36/50 [00:09<00:03, 3.64it/s]\n 74%|███████▍ | 37/50 [00:10<00:03, 3.64it/s]\n 76%|███████▌ | 38/50 [00:10<00:03, 3.64it/s]\n 78%|███████▊ | 39/50 [00:10<00:03, 3.64it/s]\n 80%|████████ | 40/50 [00:10<00:02, 3.64it/s]\n 82%|████████▏ | 41/50 [00:11<00:02, 3.64it/s]\n 84%|████████▍ | 42/50 [00:11<00:02, 3.64it/s]\n 86%|████████▌ | 43/50 [00:11<00:01, 3.64it/s]\n 88%|████████▊ | 44/50 [00:12<00:01, 3.63it/s]\n 90%|█████████ | 45/50 [00:12<00:01, 3.63it/s]\n 92%|█████████▏| 46/50 [00:12<00:01, 3.63it/s]\n 94%|█████████▍| 47/50 [00:12<00:00, 3.63it/s]\n 96%|█████████▌| 48/50 [00:13<00:00, 3.63it/s]\n 98%|█████████▊| 49/50 [00:13<00:00, 3.63it/s]\n100%|██████████| 50/50 [00:13<00:00, 3.63it/s]\n100%|██████████| 50/50 [00:13<00:00, 3.64it/s]", "metrics": { "predict_time": 15.651659, "total_time": 15.654885 }, "output": [ "https://replicate.delivery/pbxt/QQjaailiCdL5NlwJv7kSyNVYpNVat2KRXFxfNxgDr5hIDCuIA/out-0.png" ], "started_at": "2023-08-20T22:11:14.808137Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/n3qghglb5eycp7rm5p5aiqjhtu", "cancel": "https://api.replicate.com/v1/predictions/n3qghglb5eycp7rm5p5aiqjhtu/cancel" }, "version": "26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d" }Generated inUsing seed: 64800 Prompt: A cross section <s0><s1> of an iphone txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:13, 3.67it/s] 4%|▍ | 2/50 [00:00<00:13, 3.65it/s] 6%|▌ | 3/50 [00:00<00:12, 3.65it/s] 8%|▊ | 4/50 [00:01<00:12, 3.65it/s] 10%|█ | 5/50 [00:01<00:12, 3.66it/s] 12%|█▏ | 6/50 [00:01<00:12, 3.66it/s] 14%|█▍ | 7/50 [00:01<00:11, 3.66it/s] 16%|█▌ | 8/50 [00:02<00:11, 3.66it/s] 18%|█▊ | 9/50 [00:02<00:11, 3.66it/s] 20%|██ | 10/50 [00:02<00:10, 3.66it/s] 22%|██▏ | 11/50 [00:03<00:10, 3.65it/s] 24%|██▍ | 12/50 [00:03<00:10, 3.65it/s] 26%|██▌ | 13/50 [00:03<00:10, 3.65it/s] 28%|██▊ | 14/50 [00:03<00:09, 3.65it/s] 30%|███ | 15/50 [00:04<00:09, 3.65it/s] 32%|███▏ | 16/50 [00:04<00:09, 3.65it/s] 34%|███▍ | 17/50 [00:04<00:09, 3.65it/s] 36%|███▌ | 18/50 [00:04<00:08, 3.65it/s] 38%|███▊ | 19/50 [00:05<00:08, 3.65it/s] 40%|████ | 20/50 [00:05<00:08, 3.65it/s] 42%|████▏ | 21/50 [00:05<00:07, 3.65it/s] 44%|████▍ | 22/50 [00:06<00:07, 3.65it/s] 46%|████▌ | 23/50 [00:06<00:07, 3.65it/s] 48%|████▊ | 24/50 [00:06<00:07, 3.65it/s] 50%|█████ | 25/50 [00:06<00:06, 3.65it/s] 52%|█████▏ | 26/50 [00:07<00:06, 3.65it/s] 54%|█████▍ | 27/50 [00:07<00:06, 3.65it/s] 56%|█████▌ | 28/50 [00:07<00:06, 3.65it/s] 58%|█████▊ | 29/50 [00:07<00:05, 3.65it/s] 60%|██████ | 30/50 [00:08<00:05, 3.64it/s] 62%|██████▏ | 31/50 [00:08<00:05, 3.64it/s] 64%|██████▍ | 32/50 [00:08<00:04, 3.64it/s] 66%|██████▌ | 33/50 [00:09<00:04, 3.64it/s] 68%|██████▊ | 34/50 [00:09<00:04, 3.64it/s] 70%|███████ | 35/50 [00:09<00:04, 3.64it/s] 72%|███████▏ | 36/50 [00:09<00:03, 3.64it/s] 74%|███████▍ | 37/50 [00:10<00:03, 3.64it/s] 76%|███████▌ | 38/50 [00:10<00:03, 3.64it/s] 78%|███████▊ | 39/50 [00:10<00:03, 3.64it/s] 80%|████████ | 40/50 [00:10<00:02, 3.64it/s] 82%|████████▏ | 41/50 [00:11<00:02, 3.64it/s] 84%|████████▍ | 42/50 [00:11<00:02, 3.64it/s] 86%|████████▌ | 43/50 [00:11<00:01, 3.64it/s] 88%|████████▊ | 44/50 [00:12<00:01, 3.63it/s] 90%|█████████ | 45/50 [00:12<00:01, 3.63it/s] 92%|█████████▏| 46/50 [00:12<00:01, 3.63it/s] 94%|█████████▍| 47/50 [00:12<00:00, 3.63it/s] 96%|█████████▌| 48/50 [00:13<00:00, 3.63it/s] 98%|█████████▊| 49/50 [00:13<00:00, 3.63it/s] 100%|██████████| 50/50 [00:13<00:00, 3.63it/s] 100%|██████████| 50/50 [00:13<00:00, 3.64it/s]Prediction
fofr/sdxl-cross-section:26d3c19fIDehzejtlbf7oietmy6da2vytx7uStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1152
- height
- 768
- prompt
- A TOK cross section of a cyberpunk car, detailed, sharp, unreal engine
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.9
- negative_prompt
- cropped, text, soft, blurry
- prompt_strength
- 0.8
- num_inference_steps
- 40
{ "width": 1152, "height": 768, "prompt": "A TOK cross section of a cyberpunk car, detailed, sharp, unreal engine", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "cropped, text, soft, blurry", "prompt_strength": 0.8, "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run fofr/sdxl-cross-section using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-cross-section:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", { input: { width: 1152, height: 768, prompt: "A TOK cross section of a cyberpunk car, detailed, sharp, unreal engine", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.9, negative_prompt: "cropped, text, soft, blurry", prompt_strength: 0.8, num_inference_steps: 40 } } ); console.log(output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicateSet theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Import the client:import replicateRun fofr/sdxl-cross-section using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-cross-section:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", input={ "width": 1152, "height": 768, "prompt": "A TOK cross section of a cyberpunk car, detailed, sharp, unreal engine", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.9, "negative_prompt": "cropped, text, soft, blurry", "prompt_strength": 0.8, "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKENenvironment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run fofr/sdxl-cross-section 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": "26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d", "input": { "width": 1152, "height": 768, "prompt": "A TOK cross section of a cyberpunk car, detailed, sharp, unreal engine", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "cropped, text, soft, blurry", "prompt_strength": 0.8, "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/fofr/sdxl-cross-section@sha256:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d \ -i 'width=1152' \ -i 'height=768' \ -i 'prompt="A TOK cross section of a cyberpunk car, detailed, sharp, unreal engine"' \ -i 'refine="expert_ensemble_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=false' \ -i 'high_noise_frac=0.9' \ -i 'negative_prompt="cropped, text, soft, blurry"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=40'To learn more, take a look at the Cog documentation.
Run this to download the model and run it in your local environment:
docker run -d -p 5000:5000 --gpus=all r8.im/fofr/sdxl-cross-section@sha256:26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1dcurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1152, "height": 768, "prompt": "A TOK cross section of a cyberpunk car, detailed, sharp, unreal engine", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "cropped, text, soft, blurry", "prompt_strength": 0.8, "num_inference_steps": 40 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-08-20T22:34:42.452268Z", "created_at": "2023-08-20T22:34:31.633907Z", "data_removed": false, "error": null, "id": "ehzejtlbf7oietmy6da2vytx7u", "input": { "width": 1152, "height": 768, "prompt": "A TOK cross section of a cyberpunk car, detailed, sharp, unreal engine", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "cropped, text, soft, blurry", "prompt_strength": 0.8, "num_inference_steps": 40 }, "logs": "Using seed: 56318\nPrompt: A <s0><s1> cross section of a cyberpunk car, detailed, sharp, unreal engine\ntxt2img mode\n 0%| | 0/36 [00:00<?, ?it/s]\n 3%|▎ | 1/36 [00:00<00:08, 4.13it/s]\n 6%|▌ | 2/36 [00:00<00:08, 4.22it/s]\n 8%|▊ | 3/36 [00:00<00:07, 4.24it/s]\n 11%|█ | 4/36 [00:00<00:07, 4.25it/s]\n 14%|█▍ | 5/36 [00:01<00:07, 4.27it/s]\n 17%|█▋ | 6/36 [00:01<00:07, 4.28it/s]\n 19%|█▉ | 7/36 [00:01<00:06, 4.28it/s]\n 22%|██▏ | 8/36 [00:01<00:06, 4.29it/s]\n 25%|██▌ | 9/36 [00:02<00:06, 4.29it/s]\n 28%|██▊ | 10/36 [00:02<00:06, 4.29it/s]\n 31%|███ | 11/36 [00:02<00:05, 4.29it/s]\n 33%|███▎ | 12/36 [00:02<00:05, 4.29it/s]\n 36%|███▌ | 13/36 [00:03<00:05, 4.29it/s]\n 39%|███▉ | 14/36 [00:03<00:05, 4.29it/s]\n 42%|████▏ | 15/36 [00:03<00:04, 4.29it/s]\n 44%|████▍ | 16/36 [00:03<00:04, 4.29it/s]\n 47%|████▋ | 17/36 [00:03<00:04, 4.29it/s]\n 50%|█████ | 18/36 [00:04<00:04, 4.29it/s]\n 53%|█████▎ | 19/36 [00:04<00:03, 4.29it/s]\n 56%|█████▌ | 20/36 [00:04<00:03, 4.29it/s]\n 58%|█████▊ | 21/36 [00:04<00:03, 4.29it/s]\n 61%|██████ | 22/36 [00:05<00:03, 4.29it/s]\n 64%|██████▍ | 23/36 [00:05<00:03, 4.29it/s]\n 67%|██████▋ | 24/36 [00:05<00:02, 4.29it/s]\n 69%|██████▉ | 25/36 [00:05<00:02, 4.29it/s]\n 72%|███████▏ | 26/36 [00:06<00:02, 4.29it/s]\n 75%|███████▌ | 27/36 [00:06<00:02, 4.29it/s]\n 78%|███████▊ | 28/36 [00:06<00:01, 4.28it/s]\n 81%|████████ | 29/36 [00:06<00:01, 4.29it/s]\n 83%|████████▎ | 30/36 [00:07<00:01, 4.28it/s]\n 86%|████████▌ | 31/36 [00:07<00:01, 4.28it/s]\n 89%|████████▉ | 32/36 [00:07<00:00, 4.29it/s]\n 92%|█████████▏| 33/36 [00:07<00:00, 4.28it/s]\n 94%|█████████▍| 34/36 [00:07<00:00, 4.27it/s]\n 97%|█████████▋| 35/36 [00:08<00:00, 4.27it/s]\n100%|██████████| 36/36 [00:08<00:00, 4.27it/s]\n100%|██████████| 36/36 [00:08<00:00, 4.28it/s]\n 0%| | 0/4 [00:00<?, ?it/s]\n 25%|██▌ | 1/4 [00:00<00:00, 5.25it/s]\n 50%|█████ | 2/4 [00:00<00:00, 5.39it/s]\n 75%|███████▌ | 3/4 [00:00<00:00, 5.44it/s]\n100%|██████████| 4/4 [00:00<00:00, 5.46it/s]\n100%|██████████| 4/4 [00:00<00:00, 5.43it/s]", "metrics": { "predict_time": 10.810575, "total_time": 10.818361 }, "output": [ "https://replicate.delivery/pbxt/hT6fgA2XdrwmYKdochaQDiefueycPz06fJ1L8oIh4CzJgjgLC/out-0.png" ], "started_at": "2023-08-20T22:34:31.641693Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ehzejtlbf7oietmy6da2vytx7u", "cancel": "https://api.replicate.com/v1/predictions/ehzejtlbf7oietmy6da2vytx7u/cancel" }, "version": "26d3c19f09b63925b3d974d0934cbdf33e7243189f7ff3e281b00930f648fb1d" }Generated inUsing seed: 56318 Prompt: A <s0><s1> cross section of a cyberpunk car, detailed, sharp, unreal engine txt2img mode 0%| | 0/36 [00:00<?, ?it/s] 3%|▎ | 1/36 [00:00<00:08, 4.13it/s] 6%|▌ | 2/36 [00:00<00:08, 4.22it/s] 8%|▊ | 3/36 [00:00<00:07, 4.24it/s] 11%|█ | 4/36 [00:00<00:07, 4.25it/s] 14%|█▍ | 5/36 [00:01<00:07, 4.27it/s] 17%|█▋ | 6/36 [00:01<00:07, 4.28it/s] 19%|█▉ | 7/36 [00:01<00:06, 4.28it/s] 22%|██▏ | 8/36 [00:01<00:06, 4.29it/s] 25%|██▌ | 9/36 [00:02<00:06, 4.29it/s] 28%|██▊ | 10/36 [00:02<00:06, 4.29it/s] 31%|███ | 11/36 [00:02<00:05, 4.29it/s] 33%|███▎ | 12/36 [00:02<00:05, 4.29it/s] 36%|███▌ | 13/36 [00:03<00:05, 4.29it/s] 39%|███▉ | 14/36 [00:03<00:05, 4.29it/s] 42%|████▏ | 15/36 [00:03<00:04, 4.29it/s] 44%|████▍ | 16/36 [00:03<00:04, 4.29it/s] 47%|████▋ | 17/36 [00:03<00:04, 4.29it/s] 50%|█████ | 18/36 [00:04<00:04, 4.29it/s] 53%|█████▎ | 19/36 [00:04<00:03, 4.29it/s] 56%|█████▌ | 20/36 [00:04<00:03, 4.29it/s] 58%|█████▊ | 21/36 [00:04<00:03, 4.29it/s] 61%|██████ | 22/36 [00:05<00:03, 4.29it/s] 64%|██████▍ | 23/36 [00:05<00:03, 4.29it/s] 67%|██████▋ | 24/36 [00:05<00:02, 4.29it/s] 69%|██████▉ | 25/36 [00:05<00:02, 4.29it/s] 72%|███████▏ | 26/36 [00:06<00:02, 4.29it/s] 75%|███████▌ | 27/36 [00:06<00:02, 4.29it/s] 78%|███████▊ | 28/36 [00:06<00:01, 4.28it/s] 81%|████████ | 29/36 [00:06<00:01, 4.29it/s] 83%|████████▎ | 30/36 [00:07<00:01, 4.28it/s] 86%|████████▌ | 31/36 [00:07<00:01, 4.28it/s] 89%|████████▉ | 32/36 [00:07<00:00, 4.29it/s] 92%|█████████▏| 33/36 [00:07<00:00, 4.28it/s] 94%|█████████▍| 34/36 [00:07<00:00, 4.27it/s] 97%|█████████▋| 35/36 [00:08<00:00, 4.27it/s] 100%|██████████| 36/36 [00:08<00:00, 4.27it/s] 100%|██████████| 36/36 [00:08<00:00, 4.28it/s] 0%| | 0/4 [00:00<?, ?it/s] 25%|██▌ | 1/4 [00:00<00:00, 5.25it/s] 50%|█████ | 2/4 [00:00<00:00, 5.39it/s] 75%|███████▌ | 3/4 [00:00<00:00, 5.44it/s] 100%|██████████| 4/4 [00:00<00:00, 5.46it/s] 100%|██████████| 4/4 [00:00<00:00, 5.43it/s]
Want to make some of these yourself?
Run this model