zelenioncode/realvisxl4

Realism photo with RealVisXl v4.0 ( Realistic Vision with Stable Diffusion XL )

DreamBooth safetensors model use RealVisXL

This model create picture with RealVisXL3 ( with WebUI api ).


Model for the AiPicture

Realism photo with RealVisXl v4.0 ( Realistic Vision with Stable Diffusion XL )
Prediction
zelenioncode/realvisxl4:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124dIDcc3uvedb52xgt7mb56sy7ehtwaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 42
- width
- 768
- height
- 1024
- prompt
- RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3
- scheduler
- DDIM
- guidance_scale
- 7
- number_picture
- 1
- negative_prompt
- (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
- num_inference_steps
- 30
{ "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run zelenioncode/realvisxl4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "zelenioncode/realvisxl4:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d", { input: { seed: 42, width: 768, height: 1024, prompt: "RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3", scheduler: "DDIM", guidance_scale: 7, number_picture: 1, negative_prompt: "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", num_inference_steps: 30 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run zelenioncode/realvisxl4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "zelenioncode/realvisxl4:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d", input={ "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run zelenioncode/realvisxl4 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": "zelenioncode/realvisxl4:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d", "input": { "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/zelenioncode/realvisxl4@sha256:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d \ -i 'seed=42' \ -i 'width=768' \ -i 'height=1024' \ -i 'prompt="RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3"' \ -i 'scheduler="DDIM"' \ -i 'guidance_scale=7' \ -i 'number_picture=1' \ -i 'negative_prompt="(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"' \ -i 'num_inference_steps=30'
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/zelenioncode/realvisxl4@sha256:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-20T07:54:39.305694Z", "created_at": "2024-02-20T07:54:32.235759Z", "data_removed": false, "error": null, "id": "cc3uvedb52xgt7mb56sy7ehtwa", "input": { "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 }, "logs": "{'prompt': ['RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3'], 'negative_prompt': ['(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck'], 'width': 768, 'height': 1024, 'guidance_scale': 7, 'num_inference_steps': 30, 'generator': <torch._C.Generator object at 0x7f1d3ae82cb0>}\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:04, 6.68it/s]\n 7%|▋ | 2/30 [00:00<00:04, 6.62it/s]\n 10%|█ | 3/30 [00:00<00:04, 6.59it/s]\n 13%|█▎ | 4/30 [00:00<00:03, 6.56it/s]\n 17%|█▋ | 5/30 [00:00<00:03, 6.55it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.54it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.54it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.53it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.53it/s]\n 33%|███▎ | 10/30 [00:01<00:03, 6.53it/s]\n 37%|███▋ | 11/30 [00:01<00:02, 6.53it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.53it/s]\n 43%|████▎ | 13/30 [00:01<00:02, 6.53it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.51it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.51it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.52it/s]\n 57%|█████▋ | 17/30 [00:02<00:01, 6.53it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.54it/s]\n 63%|██████▎ | 19/30 [00:02<00:01, 6.55it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 6.54it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.55it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.55it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.55it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.55it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.55it/s]\n 87%|████████▋ | 26/30 [00:03<00:00, 6.56it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.55it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.54it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.54it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.54it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.54it/s]\nStableDiffusionXLPipelineOutput(images=[<PIL.Image.Image image mode=RGB size=768x1024 at 0x7F1D543C4760>])", "metrics": { "predict_time": 7.031899, "total_time": 7.069935 }, "output": [ "https://replicate.delivery/pbxt/DBroJJpLi8KTJ1N5SzAeffdFetrIjExs5VFtCWF0ySM0LDiJB/picture_0.png" ], "started_at": "2024-02-20T07:54:32.273795Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cc3uvedb52xgt7mb56sy7ehtwa", "cancel": "https://api.replicate.com/v1/predictions/cc3uvedb52xgt7mb56sy7ehtwa/cancel" }, "version": "194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d" }
Generated in{'prompt': ['RAW photo, a portrait photo of a woman in casual clothes, natural skin, tailored black three-piece suit,skin, 8k uhd, high quality, film grain, Fujifilm XT3'], 'negative_prompt': ['(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck'], 'width': 768, 'height': 1024, 'guidance_scale': 7, 'num_inference_steps': 30, 'generator': <torch._C.Generator object at 0x7f1d3ae82cb0>} 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:04, 6.68it/s] 7%|▋ | 2/30 [00:00<00:04, 6.62it/s] 10%|█ | 3/30 [00:00<00:04, 6.59it/s] 13%|█▎ | 4/30 [00:00<00:03, 6.56it/s] 17%|█▋ | 5/30 [00:00<00:03, 6.55it/s] 20%|██ | 6/30 [00:00<00:03, 6.54it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.54it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.53it/s] 30%|███ | 9/30 [00:01<00:03, 6.53it/s] 33%|███▎ | 10/30 [00:01<00:03, 6.53it/s] 37%|███▋ | 11/30 [00:01<00:02, 6.53it/s] 40%|████ | 12/30 [00:01<00:02, 6.53it/s] 43%|████▎ | 13/30 [00:01<00:02, 6.53it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.51it/s] 50%|█████ | 15/30 [00:02<00:02, 6.51it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.52it/s] 57%|█████▋ | 17/30 [00:02<00:01, 6.53it/s] 60%|██████ | 18/30 [00:02<00:01, 6.54it/s] 63%|██████▎ | 19/30 [00:02<00:01, 6.55it/s] 67%|██████▋ | 20/30 [00:03<00:01, 6.54it/s] 70%|███████ | 21/30 [00:03<00:01, 6.55it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.55it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.55it/s] 80%|████████ | 24/30 [00:03<00:00, 6.55it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.55it/s] 87%|████████▋ | 26/30 [00:03<00:00, 6.56it/s] 90%|█████████ | 27/30 [00:04<00:00, 6.55it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.54it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.54it/s] 100%|██████████| 30/30 [00:04<00:00, 6.54it/s] 100%|██████████| 30/30 [00:04<00:00, 6.54it/s] StableDiffusionXLPipelineOutput(images=[<PIL.Image.Image image mode=RGB size=768x1024 at 0x7F1D543C4760>])
Prediction
zelenioncode/realvisxl4:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124dID23m5ct3bcgl7pvd7uynubqut4mStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 42
- width
- 768
- height
- 1024
- prompt
- RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3
- scheduler
- DDIM
- guidance_scale
- 7
- number_picture
- 1
- negative_prompt
- (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
- num_inference_steps
- 30
{ "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run zelenioncode/realvisxl4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "zelenioncode/realvisxl4:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d", { input: { seed: 42, width: 768, height: 1024, prompt: "RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3", scheduler: "DDIM", guidance_scale: 7, number_picture: 1, negative_prompt: "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", num_inference_steps: 30 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run zelenioncode/realvisxl4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "zelenioncode/realvisxl4:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d", input={ "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 } ) # To access the file URL: print(output[0].url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output[0].read())
To learn more, take a look at the guide on getting started with Python.
Run zelenioncode/realvisxl4 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": "zelenioncode/realvisxl4:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d", "input": { "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To 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 cog
If 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/zelenioncode/realvisxl4@sha256:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d \ -i 'seed=42' \ -i 'width=768' \ -i 'height=1024' \ -i 'prompt="RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3"' \ -i 'scheduler="DDIM"' \ -i 'guidance_scale=7' \ -i 'number_picture=1' \ -i 'negative_prompt="(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck"' \ -i 'num_inference_steps=30'
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/zelenioncode/realvisxl4@sha256:194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-20T07:55:06.954558Z", "created_at": "2024-02-20T07:54:59.951728Z", "data_removed": false, "error": null, "id": "23m5ct3bcgl7pvd7uynubqut4m", "input": { "seed": 42, "width": 768, "height": 1024, "prompt": "RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3", "scheduler": "DDIM", "guidance_scale": 7, "number_picture": 1, "negative_prompt": "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck", "num_inference_steps": 30 }, "logs": "{'prompt': ['RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3'], 'negative_prompt': ['(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck'], 'width': 768, 'height': 1024, 'guidance_scale': 7, 'num_inference_steps': 30, 'generator': <torch._C.Generator object at 0x7f1d8f6c81f0>}\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:04, 6.63it/s]\n 7%|▋ | 2/30 [00:00<00:04, 6.58it/s]\n 10%|█ | 3/30 [00:00<00:04, 6.55it/s]\n 13%|█▎ | 4/30 [00:00<00:03, 6.55it/s]\n 17%|█▋ | 5/30 [00:00<00:03, 6.54it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.52it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.52it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.52it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.54it/s]\n 33%|███▎ | 10/30 [00:01<00:03, 6.55it/s]\n 37%|███▋ | 11/30 [00:01<00:02, 6.55it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.55it/s]\n 43%|████▎ | 13/30 [00:01<00:02, 6.55it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.55it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.56it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.56it/s]\n 57%|█████▋ | 17/30 [00:02<00:01, 6.56it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.55it/s]\n 63%|██████▎ | 19/30 [00:02<00:01, 6.55it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 6.55it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.55it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.55it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.56it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.55it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.54it/s]\n 87%|████████▋ | 26/30 [00:03<00:00, 6.54it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.55it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.55it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.55it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.55it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.55it/s]\nStableDiffusionXLPipelineOutput(images=[<PIL.Image.Image image mode=RGB size=768x1024 at 0x7F1D543C4C40>])", "metrics": { "predict_time": 6.945061, "total_time": 7.00283 }, "output": [ "https://replicate.delivery/pbxt/bC2t65F92V5XHF9e6Jsm2mFMqb2CRif2VO3DRf6KgeolNDiJB/picture_0.png" ], "started_at": "2024-02-20T07:55:00.009497Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/23m5ct3bcgl7pvd7uynubqut4m", "cancel": "https://api.replicate.com/v1/predictions/23m5ct3bcgl7pvd7uynubqut4m/cancel" }, "version": "194f6c32973b10beafa727f3b3a5a9e9336f0656ea6d1a0e25586f4a6865124d" }
Generated in{'prompt': ['RAW photo, a portrait photo of a man in casual clothes, natural skin, tailored black three-piece suit, skin, 8k uhd, high quality, film grain, Fujifilm XT3'], 'negative_prompt': ['(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck'], 'width': 768, 'height': 1024, 'guidance_scale': 7, 'num_inference_steps': 30, 'generator': <torch._C.Generator object at 0x7f1d8f6c81f0>} 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:04, 6.63it/s] 7%|▋ | 2/30 [00:00<00:04, 6.58it/s] 10%|█ | 3/30 [00:00<00:04, 6.55it/s] 13%|█▎ | 4/30 [00:00<00:03, 6.55it/s] 17%|█▋ | 5/30 [00:00<00:03, 6.54it/s] 20%|██ | 6/30 [00:00<00:03, 6.52it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.52it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.52it/s] 30%|███ | 9/30 [00:01<00:03, 6.54it/s] 33%|███▎ | 10/30 [00:01<00:03, 6.55it/s] 37%|███▋ | 11/30 [00:01<00:02, 6.55it/s] 40%|████ | 12/30 [00:01<00:02, 6.55it/s] 43%|████▎ | 13/30 [00:01<00:02, 6.55it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.55it/s] 50%|█████ | 15/30 [00:02<00:02, 6.56it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.56it/s] 57%|█████▋ | 17/30 [00:02<00:01, 6.56it/s] 60%|██████ | 18/30 [00:02<00:01, 6.55it/s] 63%|██████▎ | 19/30 [00:02<00:01, 6.55it/s] 67%|██████▋ | 20/30 [00:03<00:01, 6.55it/s] 70%|███████ | 21/30 [00:03<00:01, 6.55it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.55it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.56it/s] 80%|████████ | 24/30 [00:03<00:00, 6.55it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.54it/s] 87%|████████▋ | 26/30 [00:03<00:00, 6.54it/s] 90%|█████████ | 27/30 [00:04<00:00, 6.55it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.55it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.55it/s] 100%|██████████| 30/30 [00:04<00:00, 6.55it/s] 100%|██████████| 30/30 [00:04<00:00, 6.55it/s] StableDiffusionXLPipelineOutput(images=[<PIL.Image.Image image mode=RGB size=768x1024 at 0x7F1D543C4C40>])
Want to make some of these yourself?
Run this model