lucataco
/
realvisxl2-lcm
RealvisXL-v2.0 with LCM LoRA - requires fewer steps (4 to 8 instead of the original 40 to 50)
Prediction
lucataco/realvisxl2-lcm:47963344IDxbpexxtb6uqgh77hbusyq34tcaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 34694
- width
- 1024
- height
- 1024
- prompt
- dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot
- scheduler
- LCM
- num_outputs
- 1
- guidance_scale
- 2
- apply_watermark
- negative_prompt
- (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth
- prompt_strength
- 0.8
- num_inference_steps
- 6
{ "seed": 34694, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 }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 lucataco/realvisxl2-lcm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/realvisxl2-lcm:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", { input: { seed: 34694, width: 1024, height: 1024, prompt: "dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", scheduler: "LCM", num_outputs: 1, guidance_scale: 2, apply_watermark: true, negative_prompt: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", prompt_strength: 0.8, num_inference_steps: 6 } } ); 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 lucataco/realvisxl2-lcm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/realvisxl2-lcm:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", input={ "seed": 34694, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": True, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } ) 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 lucataco/realvisxl2-lcm 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": "479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", "input": { "seed": 34694, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } }' \ 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/lucataco/realvisxl2-lcm@sha256:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77 \ -i 'seed=34694' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot"' \ -i 'scheduler="LCM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=2' \ -i 'apply_watermark=true' \ -i 'negative_prompt="(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=6'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/lucataco/realvisxl2-lcm@sha256:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 34694, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-11-15T23:06:59.108210Z", "created_at": "2023-11-15T23:06:56.321159Z", "data_removed": false, "error": null, "id": "xbpexxtb6uqgh77hbusyq34tca", "input": { "seed": 34694, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 }, "logs": "Using seed: 34694\nPrompt: dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot\ntxt2img mode\nThe config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n 0%| | 0/6 [00:00<?, ?it/s]\n 17%|█▋ | 1/6 [00:00<00:00, 8.94it/s]\n 33%|███▎ | 2/6 [00:00<00:00, 8.86it/s]\n 50%|█████ | 3/6 [00:00<00:00, 8.87it/s]\n 67%|██████▋ | 4/6 [00:00<00:00, 8.86it/s]\n 83%|████████▎ | 5/6 [00:00<00:00, 8.84it/s]\n100%|██████████| 6/6 [00:00<00:00, 8.82it/s]\n100%|██████████| 6/6 [00:00<00:00, 8.84it/s]", "metrics": { "predict_time": 2.750163, "total_time": 2.787051 }, "output": [ "https://replicate.delivery/pbxt/ILTzFdAenk1JLKVb7jZbEDUOUJGz7hSFFSArhCnxin7ICY8IA/out-0.png" ], "started_at": "2023-11-15T23:06:56.358047Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xbpexxtb6uqgh77hbusyq34tca", "cancel": "https://api.replicate.com/v1/predictions/xbpexxtb6uqgh77hbusyq34tca/cancel" }, "version": "479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77" }Generated inUsing seed: 34694 Prompt: dark shot, front shot, photo of a 25 y.o latino man, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot txt2img mode The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:00<00:00, 8.94it/s] 33%|███▎ | 2/6 [00:00<00:00, 8.86it/s] 50%|█████ | 3/6 [00:00<00:00, 8.87it/s] 67%|██████▋ | 4/6 [00:00<00:00, 8.86it/s] 83%|████████▎ | 5/6 [00:00<00:00, 8.84it/s] 100%|██████████| 6/6 [00:00<00:00, 8.82it/s] 100%|██████████| 6/6 [00:00<00:00, 8.84it/s]Prediction
lucataco/realvisxl2-lcm:47963344IDsq4cjdtbp4dk6lyk6kymdnt7x4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 64737
- width
- 1024
- height
- 1024
- prompt
- dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot
- scheduler
- LCM
- num_outputs
- 1
- guidance_scale
- 2
- apply_watermark
- negative_prompt
- (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth
- prompt_strength
- 0.8
- num_inference_steps
- 6
{ "seed": 64737, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 }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 lucataco/realvisxl2-lcm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/realvisxl2-lcm:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", { input: { seed: 64737, width: 1024, height: 1024, prompt: "dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", scheduler: "LCM", num_outputs: 1, guidance_scale: 2, apply_watermark: true, negative_prompt: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", prompt_strength: 0.8, num_inference_steps: 6 } } ); 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 lucataco/realvisxl2-lcm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/realvisxl2-lcm:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", input={ "seed": 64737, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": True, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } ) 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 lucataco/realvisxl2-lcm 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": "479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", "input": { "seed": 64737, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } }' \ 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/lucataco/realvisxl2-lcm@sha256:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77 \ -i 'seed=64737' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot"' \ -i 'scheduler="LCM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=2' \ -i 'apply_watermark=true' \ -i 'negative_prompt="(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=6'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/lucataco/realvisxl2-lcm@sha256:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 64737, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-11-15T23:08:39.763718Z", "created_at": "2023-11-15T23:08:37.328695Z", "data_removed": false, "error": null, "id": "sq4cjdtbp4dk6lyk6kymdnt7x4", "input": { "seed": 64737, "width": 1024, "height": 1024, "prompt": "dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 }, "logs": "Using seed: 64737\nPrompt: dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot\ntxt2img mode\nThe config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n 0%| | 0/6 [00:00<?, ?it/s]\n 17%|█▋ | 1/6 [00:00<00:00, 8.93it/s]\n 33%|███▎ | 2/6 [00:00<00:00, 8.85it/s]\n 50%|█████ | 3/6 [00:00<00:00, 8.83it/s]\n 67%|██████▋ | 4/6 [00:00<00:00, 8.82it/s]\n 83%|████████▎ | 5/6 [00:00<00:00, 8.83it/s]\n100%|██████████| 6/6 [00:00<00:00, 8.84it/s]\n100%|██████████| 6/6 [00:00<00:00, 8.84it/s]", "metrics": { "predict_time": 2.396322, "total_time": 2.435023 }, "output": [ "https://replicate.delivery/pbxt/XH5EVlNNjJ4qBh9AEfMlWEZftdQVJsibqQz1Y509Wgw2Fw4RA/out-0.png" ], "started_at": "2023-11-15T23:08:37.367396Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/sq4cjdtbp4dk6lyk6kymdnt7x4", "cancel": "https://api.replicate.com/v1/predictions/sq4cjdtbp4dk6lyk6kymdnt7x4/cancel" }, "version": "479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77" }Generated inUsing seed: 64737 Prompt: dark shot, front shot, photo of a 25 y.o latino woman, perfect eyes, natural skin, skin moles, looks at viewer, cinematic shot txt2img mode The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:00<00:00, 8.93it/s] 33%|███▎ | 2/6 [00:00<00:00, 8.85it/s] 50%|█████ | 3/6 [00:00<00:00, 8.83it/s] 67%|██████▋ | 4/6 [00:00<00:00, 8.82it/s] 83%|████████▎ | 5/6 [00:00<00:00, 8.83it/s] 100%|██████████| 6/6 [00:00<00:00, 8.84it/s] 100%|██████████| 6/6 [00:00<00:00, 8.84it/s]Prediction
lucataco/realvisxl2-lcm:47963344IDajtkbidbdtmhqbfz224adrl5leStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 2020353893
- width
- 1024
- height
- 1024
- prompt
- front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)
- scheduler
- LCM
- num_outputs
- 1
- guidance_scale
- 2
- apply_watermark
- negative_prompt
- (worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth
- prompt_strength
- 0.8
- num_inference_steps
- 6
{ "seed": 2020353893, "width": 1024, "height": 1024, "prompt": "front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 }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 lucataco/realvisxl2-lcm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/realvisxl2-lcm:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", { input: { seed: 2020353893, width: 1024, height: 1024, prompt: "front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)", scheduler: "LCM", num_outputs: 1, guidance_scale: 2, apply_watermark: true, negative_prompt: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", prompt_strength: 0.8, num_inference_steps: 6 } } ); 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 lucataco/realvisxl2-lcm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/realvisxl2-lcm:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", input={ "seed": 2020353893, "width": 1024, "height": 1024, "prompt": "front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": True, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } ) 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 lucataco/realvisxl2-lcm 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": "479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77", "input": { "seed": 2020353893, "width": 1024, "height": 1024, "prompt": "front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } }' \ 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/lucataco/realvisxl2-lcm@sha256:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77 \ -i 'seed=2020353893' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)"' \ -i 'scheduler="LCM"' \ -i 'num_outputs=1' \ -i 'guidance_scale=2' \ -i 'apply_watermark=true' \ -i 'negative_prompt="(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=6'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/lucataco/realvisxl2-lcm@sha256:479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 2020353893, "width": 1024, "height": 1024, "prompt": "front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-11-15T23:33:21.493483Z", "created_at": "2023-11-15T23:33:18.997195Z", "data_removed": false, "error": null, "id": "ajtkbidbdtmhqbfz224adrl5le", "input": { "seed": 2020353893, "width": 1024, "height": 1024, "prompt": "front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)", "scheduler": "LCM", "num_outputs": 1, "guidance_scale": 2, "apply_watermark": true, "negative_prompt": "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth", "prompt_strength": 0.8, "num_inference_steps": 6 }, "logs": "Using seed: 2020353893\nPrompt: front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1)\ntxt2img mode\nThe config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.\n 0%| | 0/6 [00:00<?, ?it/s]\n 17%|█▋ | 1/6 [00:00<00:00, 9.04it/s]\n 33%|███▎ | 2/6 [00:00<00:00, 8.96it/s]\n 50%|█████ | 3/6 [00:00<00:00, 8.96it/s]\n 67%|██████▋ | 4/6 [00:00<00:00, 8.97it/s]\n 83%|████████▎ | 5/6 [00:00<00:00, 8.97it/s]\n100%|██████████| 6/6 [00:00<00:00, 8.98it/s]\n100%|██████████| 6/6 [00:00<00:00, 8.97it/s]", "metrics": { "predict_time": 2.463097, "total_time": 2.496288 }, "output": [ "https://replicate.delivery/pbxt/IUojxc6ARB4hNNVRDn8eLPdh0GrcRi4Gu11ePPevYe8C0BjHB/out-0.png" ], "started_at": "2023-11-15T23:33:19.030386Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ajtkbidbdtmhqbfz224adrl5le", "cancel": "https://api.replicate.com/v1/predictions/ajtkbidbdtmhqbfz224adrl5le/cancel" }, "version": "479633443fc6588e1e8ae764b79cdb3702d0c196e0cb2de6db39ce577383be77" }Generated inUsing seed: 2020353893 Prompt: front shot, portrait photo of a cute 22 y.o woman, looks away, full lips, natural skin, skin moles, stormy weather, (cinematic, film grain:1.1) txt2img mode The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file. 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:00<00:00, 9.04it/s] 33%|███▎ | 2/6 [00:00<00:00, 8.96it/s] 50%|█████ | 3/6 [00:00<00:00, 8.96it/s] 67%|██████▋ | 4/6 [00:00<00:00, 8.97it/s] 83%|████████▎ | 5/6 [00:00<00:00, 8.97it/s] 100%|██████████| 6/6 [00:00<00:00, 8.98it/s] 100%|██████████| 6/6 [00:00<00:00, 8.97it/s]
Want to make some of these yourself?
Run this model