fermatresearch/photorealistic-fx

RunDiffusion FX Photorealistic model, developed by RunDiffusion.

ControlNet implementation for RunDiffusion's PhotorealisticFX model.

Photorealistic FX by RunDiffusion with LoRA integrated. Works as good or better than RealisticVision.

SDXL with prompt weighting available using Compel's syntax. Check the Github link for the docs.

'''Last update: Now supports img2img.''' SDXL Canny controlnet with LoRA support.

An extremely fast all-in-one model to use LCM with SDXL, ControlNet and custom LoRA url's!

Very fast img2img for a collaboration with AI in real time

An improved outpainting model that supports LoRA urls. This model uses PatchMatch to improve the mask quality.

UPDATE: new upscaling algorithm for a much improved image quality. Fermat.app open-source implementation of an efficient ControlNet 1.1 tile for high-quality upscales. Increase the creativity to encourage hallucination.

DPO-SDXL Canny controlnet with LoRA support.

Better than SDXL at both prompt adherence and image quality, by dataautogpt3

A better alternative to SDXL refiners, providing a lot of quality and detail. Can also be used for inpainting or upscaling.

Great image quality, good old SDXL with a new and improved Tile refiner.

Restyle an image with the style of another one. I strongly suggest to upscale the results with Clarity AI

Good old controlnet + inpaint + lora

Run inpainting with Flux, compatible with Canny ControlNet, LoRAs and HyperFlux_8step

A F5-TTS fine-tuned for Spanish

A Cog implementation of BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation [Face Parsing] (https://github.com/yakhyo/face-parsing).
Prediction
fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3eID6tdda4zbxwgkw7k6nazxb6dzhuStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- "768"
- height
- "640"
- prompt
- a zoo of alien animals floating in space
- scheduler
- K_EULER_ANCESTRAL
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- (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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": "768", "height": "640", "prompt": "a zoo of alien animals floating in space", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", { input: { width: "768", height: "640", prompt: "a zoo of alien animals floating in space", scheduler: "K_EULER_ANCESTRAL", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "(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", prompt_strength: 0.8, 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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", input={ "width": "768", "height": "640", "prompt": "a zoo of alien animals floating in space", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx 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": "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", "input": { "width": "768", "height": "640", "prompt": "a zoo of alien animals floating in space", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-06-13T13:14:35.944840Z", "created_at": "2023-06-13T13:14:32.535556Z", "data_removed": false, "error": null, "id": "6tdda4zbxwgkw7k6nazxb6dzhu", "input": { "width": "768", "height": "640", "prompt": "a zoo of alien animals floating in space", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 9582\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:02, 9.75it/s]\n 10%|█ | 3/30 [00:00<00:02, 11.33it/s]\n 17%|█▋ | 5/30 [00:00<00:02, 11.68it/s]\n 23%|██▎ | 7/30 [00:00<00:01, 11.82it/s]\n 30%|███ | 9/30 [00:00<00:01, 11.80it/s]\n 37%|███▋ | 11/30 [00:00<00:01, 11.87it/s]\n 43%|████▎ | 13/30 [00:01<00:01, 11.70it/s]\n 50%|█████ | 15/30 [00:01<00:01, 11.81it/s]\n 57%|█████▋ | 17/30 [00:01<00:01, 11.87it/s]\n 63%|██████▎ | 19/30 [00:01<00:00, 11.92it/s]\n 70%|███████ | 21/30 [00:01<00:00, 11.90it/s]\n 77%|███████▋ | 23/30 [00:01<00:00, 11.91it/s]\n 83%|████████▎ | 25/30 [00:02<00:00, 11.95it/s]\n 90%|█████████ | 27/30 [00:02<00:00, 11.94it/s]\n 97%|█████████▋| 29/30 [00:02<00:00, 11.96it/s]\n100%|██████████| 30/30 [00:02<00:00, 11.83it/s]", "metrics": { "predict_time": 3.533685, "total_time": 3.409284 }, "output": [ "https://replicate.delivery/pbxt/Gs5eJCFuLDT8YSnfHEuNsk8y0LpwtUBQe5iMjDcqfHeY3OsIC/out-0.png" ], "started_at": "2023-06-13T13:14:32.411155Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/6tdda4zbxwgkw7k6nazxb6dzhu", "cancel": "https://api.replicate.com/v1/predictions/6tdda4zbxwgkw7k6nazxb6dzhu/cancel" }, "version": "580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e" }
Generated inUsing seed: 9582 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:02, 9.75it/s] 10%|█ | 3/30 [00:00<00:02, 11.33it/s] 17%|█▋ | 5/30 [00:00<00:02, 11.68it/s] 23%|██▎ | 7/30 [00:00<00:01, 11.82it/s] 30%|███ | 9/30 [00:00<00:01, 11.80it/s] 37%|███▋ | 11/30 [00:00<00:01, 11.87it/s] 43%|████▎ | 13/30 [00:01<00:01, 11.70it/s] 50%|█████ | 15/30 [00:01<00:01, 11.81it/s] 57%|█████▋ | 17/30 [00:01<00:01, 11.87it/s] 63%|██████▎ | 19/30 [00:01<00:00, 11.92it/s] 70%|███████ | 21/30 [00:01<00:00, 11.90it/s] 77%|███████▋ | 23/30 [00:01<00:00, 11.91it/s] 83%|████████▎ | 25/30 [00:02<00:00, 11.95it/s] 90%|█████████ | 27/30 [00:02<00:00, 11.94it/s] 97%|█████████▋| 29/30 [00:02<00:00, 11.96it/s] 100%|██████████| 30/30 [00:02<00:00, 11.83it/s]
Prediction
fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3eIDkam6agjbz5hjuahlr2dz3oeqraStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 768
- height
- 640
- prompt
- retro ferrari enzo in Golden Gate bridge, epic sunset
- scheduler
- K_EULER_ANCESTRAL
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- (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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 768, "height": 640, "prompt": "retro ferrari enzo in Golden Gate bridge, epic sunset", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", { input: { width: 768, height: 640, prompt: "retro ferrari enzo in Golden Gate bridge, epic sunset", scheduler: "K_EULER_ANCESTRAL", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "(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", prompt_strength: 0.8, 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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", input={ "width": 768, "height": 640, "prompt": "retro ferrari enzo in Golden Gate bridge, epic sunset", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx 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": "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", "input": { "width": 768, "height": 640, "prompt": "retro ferrari enzo in Golden Gate bridge, epic sunset", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-06-13T13:26:22.326100Z", "created_at": "2023-06-13T13:26:18.455918Z", "data_removed": false, "error": null, "id": "kam6agjbz5hjuahlr2dz3oeqra", "input": { "width": 768, "height": 640, "prompt": "retro ferrari enzo in Golden Gate bridge, epic sunset", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 28589\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:02, 9.71it/s]\n 7%|▋ | 2/30 [00:00<00:02, 9.45it/s]\n 13%|█▎ | 4/30 [00:00<00:02, 9.89it/s]\n 17%|█▋ | 5/30 [00:00<00:02, 9.75it/s]\n 20%|██ | 6/30 [00:00<00:02, 9.82it/s]\n 23%|██▎ | 7/30 [00:00<00:02, 9.84it/s]\n 30%|███ | 9/30 [00:00<00:02, 10.28it/s]\n 37%|███▋ | 11/30 [00:01<00:01, 10.27it/s]\n 43%|████▎ | 13/30 [00:01<00:01, 10.32it/s]\n 50%|█████ | 15/30 [00:01<00:01, 10.43it/s]\n 57%|█████▋ | 17/30 [00:01<00:01, 10.46it/s]\n 63%|██████▎ | 19/30 [00:01<00:01, 10.47it/s]\n 70%|███████ | 21/30 [00:02<00:00, 10.53it/s]\n 77%|███████▋ | 23/30 [00:02<00:00, 10.62it/s]\n 83%|████████▎ | 25/30 [00:02<00:00, 10.47it/s]\n 90%|█████████ | 27/30 [00:02<00:00, 10.41it/s]\n 97%|█████████▋| 29/30 [00:02<00:00, 10.30it/s]\n100%|██████████| 30/30 [00:02<00:00, 10.29it/s]", "metrics": { "predict_time": 3.903681, "total_time": 3.870182 }, "output": [ "https://replicate.delivery/pbxt/A1R8ravDBWpnIZKrEVii3jKy62keWXef45Te3fyhIqOqPQsIC/out-0.png" ], "started_at": "2023-06-13T13:26:18.422419Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/kam6agjbz5hjuahlr2dz3oeqra", "cancel": "https://api.replicate.com/v1/predictions/kam6agjbz5hjuahlr2dz3oeqra/cancel" }, "version": "580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e" }
Generated inUsing seed: 28589 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:02, 9.71it/s] 7%|▋ | 2/30 [00:00<00:02, 9.45it/s] 13%|█▎ | 4/30 [00:00<00:02, 9.89it/s] 17%|█▋ | 5/30 [00:00<00:02, 9.75it/s] 20%|██ | 6/30 [00:00<00:02, 9.82it/s] 23%|██▎ | 7/30 [00:00<00:02, 9.84it/s] 30%|███ | 9/30 [00:00<00:02, 10.28it/s] 37%|███▋ | 11/30 [00:01<00:01, 10.27it/s] 43%|████▎ | 13/30 [00:01<00:01, 10.32it/s] 50%|█████ | 15/30 [00:01<00:01, 10.43it/s] 57%|█████▋ | 17/30 [00:01<00:01, 10.46it/s] 63%|██████▎ | 19/30 [00:01<00:01, 10.47it/s] 70%|███████ | 21/30 [00:02<00:00, 10.53it/s] 77%|███████▋ | 23/30 [00:02<00:00, 10.62it/s] 83%|████████▎ | 25/30 [00:02<00:00, 10.47it/s] 90%|█████████ | 27/30 [00:02<00:00, 10.41it/s] 97%|█████████▋| 29/30 [00:02<00:00, 10.30it/s] 100%|██████████| 30/30 [00:02<00:00, 10.29it/s]
Prediction
fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3eID44hw5mrbwoamajcdzrfhwfzgoqStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 768
- height
- "1024"
- prompt
- an old library with nostalgic vibe, dark image
- scheduler
- K_EULER_ANCESTRAL
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- (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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 768, "height": "1024", "prompt": "an old library with nostalgic vibe, dark image", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", { input: { width: 768, height: "1024", prompt: "an old library with nostalgic vibe, dark image", scheduler: "K_EULER_ANCESTRAL", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "(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", prompt_strength: 0.8, 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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", input={ "width": 768, "height": "1024", "prompt": "an old library with nostalgic vibe, dark image", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx 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": "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", "input": { "width": 768, "height": "1024", "prompt": "an old library with nostalgic vibe, dark image", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-06-13T13:27:36.614192Z", "created_at": "2023-06-13T13:27:30.984228Z", "data_removed": false, "error": null, "id": "44hw5mrbwoamajcdzrfhwfzgoq", "input": { "width": 768, "height": "1024", "prompt": "an old library with nostalgic vibe, dark image", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 47014\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:06, 4.49it/s]\n 7%|▋ | 2/30 [00:00<00:05, 5.38it/s]\n 10%|█ | 3/30 [00:00<00:04, 5.93it/s]\n 13%|█▎ | 4/30 [00:00<00:04, 6.24it/s]\n 17%|█▋ | 5/30 [00:00<00:03, 6.43it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.55it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.62it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.67it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.70it/s]\n 33%|███▎ | 10/30 [00:01<00:02, 6.73it/s]\n 37%|███▋ | 11/30 [00:01<00:02, 6.75it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.75it/s]\n 43%|████▎ | 13/30 [00:02<00:02, 6.76it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.76it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.77it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.77it/s]\n 57%|█████▋ | 17/30 [00:02<00:01, 6.78it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.78it/s]\n 63%|██████▎ | 19/30 [00:02<00:01, 6.78it/s]\n 67%|██████▋ | 20/30 [00:03<00:01, 6.77it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.77it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.78it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.77it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.78it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.78it/s]\n 87%|████████▋ | 26/30 [00:03<00:00, 6.78it/s]\n 90%|█████████ | 27/30 [00:04<00:00, 6.78it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.78it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.78it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.78it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.65it/s]", "metrics": { "predict_time": 5.659261, "total_time": 5.629964 }, "output": [ "https://replicate.delivery/pbxt/zTXQgUuYup7fS6jfJb8bFkj6eCbR1wgk4Zao47x1OSDOGELiA/out-0.png" ], "started_at": "2023-06-13T13:27:30.954931Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/44hw5mrbwoamajcdzrfhwfzgoq", "cancel": "https://api.replicate.com/v1/predictions/44hw5mrbwoamajcdzrfhwfzgoq/cancel" }, "version": "580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e" }
Generated inUsing seed: 47014 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:06, 4.49it/s] 7%|▋ | 2/30 [00:00<00:05, 5.38it/s] 10%|█ | 3/30 [00:00<00:04, 5.93it/s] 13%|█▎ | 4/30 [00:00<00:04, 6.24it/s] 17%|█▋ | 5/30 [00:00<00:03, 6.43it/s] 20%|██ | 6/30 [00:00<00:03, 6.55it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.62it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.67it/s] 30%|███ | 9/30 [00:01<00:03, 6.70it/s] 33%|███▎ | 10/30 [00:01<00:02, 6.73it/s] 37%|███▋ | 11/30 [00:01<00:02, 6.75it/s] 40%|████ | 12/30 [00:01<00:02, 6.75it/s] 43%|████▎ | 13/30 [00:02<00:02, 6.76it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.76it/s] 50%|█████ | 15/30 [00:02<00:02, 6.77it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.77it/s] 57%|█████▋ | 17/30 [00:02<00:01, 6.78it/s] 60%|██████ | 18/30 [00:02<00:01, 6.78it/s] 63%|██████▎ | 19/30 [00:02<00:01, 6.78it/s] 67%|██████▋ | 20/30 [00:03<00:01, 6.77it/s] 70%|███████ | 21/30 [00:03<00:01, 6.77it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.78it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.77it/s] 80%|████████ | 24/30 [00:03<00:00, 6.78it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.78it/s] 87%|████████▋ | 26/30 [00:03<00:00, 6.78it/s] 90%|█████████ | 27/30 [00:04<00:00, 6.78it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.78it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.78it/s] 100%|██████████| 30/30 [00:04<00:00, 6.78it/s] 100%|██████████| 30/30 [00:04<00:00, 6.65it/s]
Prediction
fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3eID6sikprbb57npscqgq3ax5febk4StatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- "1024"
- height
- "448"
- prompt
- panoramic view of Barcelona, skyline, epic sunset
- scheduler
- K_EULER_ANCESTRAL
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- (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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": "1024", "height": "448", "prompt": "panoramic view of Barcelona, skyline, epic sunset", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", { input: { width: "1024", height: "448", prompt: "panoramic view of Barcelona, skyline, epic sunset", scheduler: "K_EULER_ANCESTRAL", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "(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", prompt_strength: 0.8, 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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", input={ "width": "1024", "height": "448", "prompt": "panoramic view of Barcelona, skyline, epic sunset", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx 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": "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", "input": { "width": "1024", "height": "448", "prompt": "panoramic view of Barcelona, skyline, epic sunset", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-06-13T13:29:34.851968Z", "created_at": "2023-06-13T13:29:31.537804Z", "data_removed": false, "error": null, "id": "6sikprbb57npscqgq3ax5febk4", "input": { "width": "1024", "height": "448", "prompt": "panoramic view of Barcelona, skyline, epic sunset", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(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", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 64200\n 0%| | 0/30 [00:00<?, ?it/s]\n 7%|▋ | 2/30 [00:00<00:02, 11.02it/s]\n 13%|█▎ | 4/30 [00:00<00:02, 11.51it/s]\n 20%|██ | 6/30 [00:00<00:02, 11.95it/s]\n 27%|██▋ | 8/30 [00:00<00:01, 12.11it/s]\n 33%|███▎ | 10/30 [00:00<00:01, 12.27it/s]\n 40%|████ | 12/30 [00:00<00:01, 12.41it/s]\n 47%|████▋ | 14/30 [00:01<00:01, 12.51it/s]\n 53%|█████▎ | 16/30 [00:01<00:01, 12.55it/s]\n 60%|██████ | 18/30 [00:01<00:00, 12.61it/s]\n 67%|██████▋ | 20/30 [00:01<00:00, 12.58it/s]\n 73%|███████▎ | 22/30 [00:01<00:00, 12.58it/s]\n 80%|████████ | 24/30 [00:01<00:00, 12.61it/s]\n 87%|████████▋ | 26/30 [00:02<00:00, 12.59it/s]\n 93%|█████████▎| 28/30 [00:02<00:00, 12.59it/s]\n100%|██████████| 30/30 [00:02<00:00, 12.60it/s]\n100%|██████████| 30/30 [00:02<00:00, 12.43it/s]", "metrics": { "predict_time": 3.342138, "total_time": 3.314164 }, "output": [ "https://replicate.delivery/pbxt/N7DtCgnEsS63EN42f7Y1wWRut63QbKjQFe2P1ieqIGR9JELiA/out-0.png" ], "started_at": "2023-06-13T13:29:31.509830Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/6sikprbb57npscqgq3ax5febk4", "cancel": "https://api.replicate.com/v1/predictions/6sikprbb57npscqgq3ax5febk4/cancel" }, "version": "580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e" }
Generated inUsing seed: 64200 0%| | 0/30 [00:00<?, ?it/s] 7%|▋ | 2/30 [00:00<00:02, 11.02it/s] 13%|█▎ | 4/30 [00:00<00:02, 11.51it/s] 20%|██ | 6/30 [00:00<00:02, 11.95it/s] 27%|██▋ | 8/30 [00:00<00:01, 12.11it/s] 33%|███▎ | 10/30 [00:00<00:01, 12.27it/s] 40%|████ | 12/30 [00:00<00:01, 12.41it/s] 47%|████▋ | 14/30 [00:01<00:01, 12.51it/s] 53%|█████▎ | 16/30 [00:01<00:01, 12.55it/s] 60%|██████ | 18/30 [00:01<00:00, 12.61it/s] 67%|██████▋ | 20/30 [00:01<00:00, 12.58it/s] 73%|███████▎ | 22/30 [00:01<00:00, 12.58it/s] 80%|████████ | 24/30 [00:01<00:00, 12.61it/s] 87%|████████▋ | 26/30 [00:02<00:00, 12.59it/s] 93%|█████████▎| 28/30 [00:02<00:00, 12.59it/s] 100%|██████████| 30/30 [00:02<00:00, 12.60it/s] 100%|██████████| 30/30 [00:02<00:00, 12.43it/s]
Prediction
fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3eID7zjbjarbwfds3tgvc7jt2i54zuStatusSucceededSourceWebHardwareA100 (40GB)Total durationCreatedInput
- width
- 768
- height
- "1024"
- prompt
- close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting
- scheduler
- K_EULER_ANCESTRAL
- num_outputs
- 1
- guidance_scale
- 7.5
- negative_prompt
- (semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 768, "height": "1024", "prompt": "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", { input: { width: 768, height: "1024", prompt: "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting", scheduler: "K_EULER_ANCESTRAL", num_outputs: 1, guidance_scale: 7.5, negative_prompt: "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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", prompt_strength: 0.8, 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 fermatresearch/photorealistic-fx using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", input={ "width": 768, "height": "1024", "prompt": "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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", "prompt_strength": 0.8, "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 fermatresearch/photorealistic-fx 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": "fermatresearch/photorealistic-fx:580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e", "input": { "width": 768, "height": "1024", "prompt": "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-06-13T13:33:10.227866Z", "created_at": "2023-06-13T13:33:04.674532Z", "data_removed": false, "error": null, "id": "7zjbjarbwfds3tgvc7jt2i54zu", "input": { "width": 768, "height": "1024", "prompt": "close up of a tiger staring at the camera with a fierce expression and the mouth open, bokeh effect, jungle, sharp teeth, hunting", "scheduler": "K_EULER_ANCESTRAL", "num_outputs": 1, "guidance_scale": 7.5, "negative_prompt": "(semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, 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", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 30772\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:05, 5.69it/s]\n 7%|▋ | 2/30 [00:00<00:04, 6.29it/s]\n 10%|█ | 3/30 [00:00<00:04, 6.51it/s]\n 13%|█▎ | 4/30 [00:00<00:03, 6.62it/s]\n 17%|█▋ | 5/30 [00:00<00:03, 6.69it/s]\n 20%|██ | 6/30 [00:00<00:03, 6.73it/s]\n 23%|██▎ | 7/30 [00:01<00:03, 6.74it/s]\n 27%|██▋ | 8/30 [00:01<00:03, 6.76it/s]\n 30%|███ | 9/30 [00:01<00:03, 6.78it/s]\n 33%|███▎ | 10/30 [00:01<00:02, 6.79it/s]\n 37%|███▋ | 11/30 [00:01<00:02, 6.80it/s]\n 40%|████ | 12/30 [00:01<00:02, 6.80it/s]\n 43%|████▎ | 13/30 [00:01<00:02, 6.80it/s]\n 47%|████▋ | 14/30 [00:02<00:02, 6.80it/s]\n 50%|█████ | 15/30 [00:02<00:02, 6.81it/s]\n 53%|█████▎ | 16/30 [00:02<00:02, 6.81it/s]\n 57%|█████▋ | 17/30 [00:02<00:01, 6.80it/s]\n 60%|██████ | 18/30 [00:02<00:01, 6.80it/s]\n 63%|██████▎ | 19/30 [00:02<00:01, 6.80it/s]\n 67%|██████▋ | 20/30 [00:02<00:01, 6.80it/s]\n 70%|███████ | 21/30 [00:03<00:01, 6.80it/s]\n 73%|███████▎ | 22/30 [00:03<00:01, 6.80it/s]\n 77%|███████▋ | 23/30 [00:03<00:01, 6.80it/s]\n 80%|████████ | 24/30 [00:03<00:00, 6.80it/s]\n 83%|████████▎ | 25/30 [00:03<00:00, 6.80it/s]\n 87%|████████▋ | 26/30 [00:03<00:00, 6.81it/s]\n 90%|█████████ | 27/30 [00:03<00:00, 6.81it/s]\n 93%|█████████▎| 28/30 [00:04<00:00, 6.81it/s]\n 97%|█████████▋| 29/30 [00:04<00:00, 6.80it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.81it/s]\n100%|██████████| 30/30 [00:04<00:00, 6.76it/s]", "metrics": { "predict_time": 5.591633, "total_time": 5.553334 }, "output": [ "https://replicate.delivery/pbxt/DTtIuZRWFiojIJG3ZABnY2e7pf4oTlxxgjYvzouRnUCVIiFRA/out-0.png" ], "started_at": "2023-06-13T13:33:04.636233Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/7zjbjarbwfds3tgvc7jt2i54zu", "cancel": "https://api.replicate.com/v1/predictions/7zjbjarbwfds3tgvc7jt2i54zu/cancel" }, "version": "580cd5e6de394d3ced207a7e4275d7d9b7e0174212f3bbe108e290e25a859a3e" }
Generated inUsing seed: 30772 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:05, 5.69it/s] 7%|▋ | 2/30 [00:00<00:04, 6.29it/s] 10%|█ | 3/30 [00:00<00:04, 6.51it/s] 13%|█▎ | 4/30 [00:00<00:03, 6.62it/s] 17%|█▋ | 5/30 [00:00<00:03, 6.69it/s] 20%|██ | 6/30 [00:00<00:03, 6.73it/s] 23%|██▎ | 7/30 [00:01<00:03, 6.74it/s] 27%|██▋ | 8/30 [00:01<00:03, 6.76it/s] 30%|███ | 9/30 [00:01<00:03, 6.78it/s] 33%|███▎ | 10/30 [00:01<00:02, 6.79it/s] 37%|███▋ | 11/30 [00:01<00:02, 6.80it/s] 40%|████ | 12/30 [00:01<00:02, 6.80it/s] 43%|████▎ | 13/30 [00:01<00:02, 6.80it/s] 47%|████▋ | 14/30 [00:02<00:02, 6.80it/s] 50%|█████ | 15/30 [00:02<00:02, 6.81it/s] 53%|█████▎ | 16/30 [00:02<00:02, 6.81it/s] 57%|█████▋ | 17/30 [00:02<00:01, 6.80it/s] 60%|██████ | 18/30 [00:02<00:01, 6.80it/s] 63%|██████▎ | 19/30 [00:02<00:01, 6.80it/s] 67%|██████▋ | 20/30 [00:02<00:01, 6.80it/s] 70%|███████ | 21/30 [00:03<00:01, 6.80it/s] 73%|███████▎ | 22/30 [00:03<00:01, 6.80it/s] 77%|███████▋ | 23/30 [00:03<00:01, 6.80it/s] 80%|████████ | 24/30 [00:03<00:00, 6.80it/s] 83%|████████▎ | 25/30 [00:03<00:00, 6.80it/s] 87%|████████▋ | 26/30 [00:03<00:00, 6.81it/s] 90%|█████████ | 27/30 [00:03<00:00, 6.81it/s] 93%|█████████▎| 28/30 [00:04<00:00, 6.81it/s] 97%|█████████▋| 29/30 [00:04<00:00, 6.80it/s] 100%|██████████| 30/30 [00:04<00:00, 6.81it/s] 100%|██████████| 30/30 [00:04<00:00, 6.76it/s]
Want to make some of these yourself?
Run this model