fofr
/
sdxl-simpsons-characters
SDXL fine-tuned on MJv6 Simpsons generated images
- Public
- 30.4K runs
-
L40S
- SDXL fine-tune
Prediction
fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91IDrdtenadbhjvvwpm6snr4waws7uStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A TOK Simpsons character of a man
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- ugly, broken, distorted, artefacts, 3D, render, photography
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a man", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "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"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", { input: { width: 1024, height: 1024, prompt: "A TOK Simpsons character of a man", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "ugly, broken, distorted, artefacts, 3D, render, photography", 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 fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", input={ "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a man", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-simpsons-characters 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": "f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a man", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "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.
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/fofr/sdxl-simpsons-characters@sha256:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A TOK Simpsons character of a man"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="ugly, broken, distorted, artefacts, 3D, render, photography"' \ -i 'prompt_strength=0.8' \ -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/fofr/sdxl-simpsons-characters@sha256:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a man", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-22T16:12:23.854743Z", "created_at": "2023-12-22T16:12:13.116885Z", "data_removed": false, "error": null, "id": "rdtenadbhjvvwpm6snr4waws7u", "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a man", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 24331\nskipping loading .. weights already loaded\nPrompt: A <s0><s1> Simpsons character of a man\ntxt2img mode\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:07, 3.66it/s]\n 7%|▋ | 2/30 [00:00<00:07, 3.64it/s]\n 10%|█ | 3/30 [00:00<00:07, 3.64it/s]\n 13%|█▎ | 4/30 [00:01<00:07, 3.64it/s]\n 17%|█▋ | 5/30 [00:01<00:06, 3.63it/s]\n 20%|██ | 6/30 [00:01<00:06, 3.63it/s]\n 23%|██▎ | 7/30 [00:01<00:06, 3.63it/s]\n 27%|██▋ | 8/30 [00:02<00:06, 3.62it/s]\n 30%|███ | 9/30 [00:02<00:05, 3.62it/s]\n 33%|███▎ | 10/30 [00:02<00:05, 3.62it/s]\n 37%|███▋ | 11/30 [00:03<00:05, 3.62it/s]\n 40%|████ | 12/30 [00:03<00:04, 3.62it/s]\n 43%|████▎ | 13/30 [00:03<00:04, 3.62it/s]\n 47%|████▋ | 14/30 [00:03<00:04, 3.62it/s]\n 50%|█████ | 15/30 [00:04<00:04, 3.62it/s]\n 53%|█████▎ | 16/30 [00:04<00:03, 3.62it/s]\n 57%|█████▋ | 17/30 [00:04<00:03, 3.61it/s]\n 60%|██████ | 18/30 [00:04<00:03, 3.61it/s]\n 63%|██████▎ | 19/30 [00:05<00:03, 3.61it/s]\n 67%|██████▋ | 20/30 [00:05<00:02, 3.61it/s]\n 70%|███████ | 21/30 [00:05<00:02, 3.62it/s]\n 73%|███████▎ | 22/30 [00:06<00:02, 3.62it/s]\n 77%|███████▋ | 23/30 [00:06<00:01, 3.62it/s]\n 80%|████████ | 24/30 [00:06<00:01, 3.62it/s]\n 83%|████████▎ | 25/30 [00:06<00:01, 3.62it/s]\n 87%|████████▋ | 26/30 [00:07<00:01, 3.62it/s]\n 90%|█████████ | 27/30 [00:07<00:00, 3.61it/s]\n 93%|█████████▎| 28/30 [00:07<00:00, 3.61it/s]\n 97%|█████████▋| 29/30 [00:08<00:00, 3.61it/s]\n100%|██████████| 30/30 [00:08<00:00, 3.61it/s]\n100%|██████████| 30/30 [00:08<00:00, 3.62it/s]", "metrics": { "predict_time": 10.701728, "total_time": 10.737858 }, "output": [ "https://replicate.delivery/pbxt/VHt4ScDNf0y3f0yqJXefGcfTWhO4w71C0UrXbLUqWWevZnNhE/out-0.png" ], "started_at": "2023-12-22T16:12:13.153015Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rdtenadbhjvvwpm6snr4waws7u", "cancel": "https://api.replicate.com/v1/predictions/rdtenadbhjvvwpm6snr4waws7u/cancel" }, "version": "f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91" }
Generated inUsing seed: 24331 skipping loading .. weights already loaded Prompt: A <s0><s1> Simpsons character of a man txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:07, 3.66it/s] 7%|▋ | 2/30 [00:00<00:07, 3.64it/s] 10%|█ | 3/30 [00:00<00:07, 3.64it/s] 13%|█▎ | 4/30 [00:01<00:07, 3.64it/s] 17%|█▋ | 5/30 [00:01<00:06, 3.63it/s] 20%|██ | 6/30 [00:01<00:06, 3.63it/s] 23%|██▎ | 7/30 [00:01<00:06, 3.63it/s] 27%|██▋ | 8/30 [00:02<00:06, 3.62it/s] 30%|███ | 9/30 [00:02<00:05, 3.62it/s] 33%|███▎ | 10/30 [00:02<00:05, 3.62it/s] 37%|███▋ | 11/30 [00:03<00:05, 3.62it/s] 40%|████ | 12/30 [00:03<00:04, 3.62it/s] 43%|████▎ | 13/30 [00:03<00:04, 3.62it/s] 47%|████▋ | 14/30 [00:03<00:04, 3.62it/s] 50%|█████ | 15/30 [00:04<00:04, 3.62it/s] 53%|█████▎ | 16/30 [00:04<00:03, 3.62it/s] 57%|█████▋ | 17/30 [00:04<00:03, 3.61it/s] 60%|██████ | 18/30 [00:04<00:03, 3.61it/s] 63%|██████▎ | 19/30 [00:05<00:03, 3.61it/s] 67%|██████▋ | 20/30 [00:05<00:02, 3.61it/s] 70%|███████ | 21/30 [00:05<00:02, 3.62it/s] 73%|███████▎ | 22/30 [00:06<00:02, 3.62it/s] 77%|███████▋ | 23/30 [00:06<00:01, 3.62it/s] 80%|████████ | 24/30 [00:06<00:01, 3.62it/s] 83%|████████▎ | 25/30 [00:06<00:01, 3.62it/s] 87%|████████▋ | 26/30 [00:07<00:01, 3.62it/s] 90%|█████████ | 27/30 [00:07<00:00, 3.61it/s] 93%|█████████▎| 28/30 [00:07<00:00, 3.61it/s] 97%|█████████▋| 29/30 [00:08<00:00, 3.61it/s] 100%|██████████| 30/30 [00:08<00:00, 3.61it/s] 100%|██████████| 30/30 [00:08<00:00, 3.62it/s]
Prediction
fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91IDnikf7blbovg3p2jfr3vebhariqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A TOK Simpsons character of a woman
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- ugly, broken, distorted, artefacts, 3D, render, photography
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a woman", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "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"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", { input: { width: 1024, height: 1024, prompt: "A TOK Simpsons character of a woman", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "ugly, broken, distorted, artefacts, 3D, render, photography", 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 fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", input={ "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a woman", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-simpsons-characters 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": "f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a woman", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "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.
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/fofr/sdxl-simpsons-characters@sha256:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A TOK Simpsons character of a woman"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="ugly, broken, distorted, artefacts, 3D, render, photography"' \ -i 'prompt_strength=0.8' \ -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/fofr/sdxl-simpsons-characters@sha256:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a woman", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-22T16:13:05.407912Z", "created_at": "2023-12-22T16:12:44.261421Z", "data_removed": false, "error": null, "id": "nikf7blbovg3p2jfr3vebhariq", "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of a woman", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 25873\nEnsuring enough disk space...\nFree disk space: 1555231862784\nDownloading weights: https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\n2023-12-22T16:12:53Z | INFO | [ Initiating ] dest=/src/weights-cache/61d61cadc695e415 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\n2023-12-22T16:12:54Z | INFO | [ Complete ] dest=/src/weights-cache/61d61cadc695e415 size=\"186 MB\" total_elapsed=0.742s url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\nb''\nDownloaded weights in 0.9362092018127441 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A <s0><s1> Simpsons character of a woman\ntxt2img mode\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:07, 3.66it/s]\n 7%|▋ | 2/30 [00:00<00:07, 3.65it/s]\n 10%|█ | 3/30 [00:00<00:07, 3.65it/s]\n 13%|█▎ | 4/30 [00:01<00:07, 3.65it/s]\n 17%|█▋ | 5/30 [00:01<00:06, 3.65it/s]\n 20%|██ | 6/30 [00:01<00:06, 3.65it/s]\n 23%|██▎ | 7/30 [00:01<00:06, 3.65it/s]\n 27%|██▋ | 8/30 [00:02<00:06, 3.65it/s]\n 30%|███ | 9/30 [00:02<00:05, 3.66it/s]\n 33%|███▎ | 10/30 [00:02<00:05, 3.65it/s]\n 37%|███▋ | 11/30 [00:03<00:05, 3.65it/s]\n 40%|████ | 12/30 [00:03<00:04, 3.66it/s]\n 43%|████▎ | 13/30 [00:03<00:04, 3.66it/s]\n 47%|████▋ | 14/30 [00:03<00:04, 3.66it/s]\n 50%|█████ | 15/30 [00:04<00:04, 3.66it/s]\n 53%|█████▎ | 16/30 [00:04<00:03, 3.66it/s]\n 57%|█████▋ | 17/30 [00:04<00:03, 3.65it/s]\n 60%|██████ | 18/30 [00:04<00:03, 3.65it/s]\n 63%|██████▎ | 19/30 [00:05<00:03, 3.65it/s]\n 67%|██████▋ | 20/30 [00:05<00:02, 3.65it/s]\n 70%|███████ | 21/30 [00:05<00:02, 3.65it/s]\n 73%|███████▎ | 22/30 [00:06<00:02, 3.65it/s]\n 77%|███████▋ | 23/30 [00:06<00:01, 3.65it/s]\n 80%|████████ | 24/30 [00:06<00:01, 3.65it/s]\n 83%|████████▎ | 25/30 [00:06<00:01, 3.65it/s]\n 87%|████████▋ | 26/30 [00:07<00:01, 3.65it/s]\n 90%|█████████ | 27/30 [00:07<00:00, 3.65it/s]\n 93%|█████████▎| 28/30 [00:07<00:00, 3.64it/s]\n 97%|█████████▋| 29/30 [00:07<00:00, 3.64it/s]\n100%|██████████| 30/30 [00:08<00:00, 3.64it/s]\n100%|██████████| 30/30 [00:08<00:00, 3.65it/s]", "metrics": { "predict_time": 11.820137, "total_time": 21.146491 }, "output": [ "https://replicate.delivery/pbxt/To5Oq1igxQL5G1ippzLQbckwTMPfxRRFvo8YbGeF4kZQesJkA/out-0.png" ], "started_at": "2023-12-22T16:12:53.587775Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/nikf7blbovg3p2jfr3vebhariq", "cancel": "https://api.replicate.com/v1/predictions/nikf7blbovg3p2jfr3vebhariq/cancel" }, "version": "f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91" }
Generated inUsing seed: 25873 Ensuring enough disk space... Free disk space: 1555231862784 Downloading weights: https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar 2023-12-22T16:12:53Z | INFO | [ Initiating ] dest=/src/weights-cache/61d61cadc695e415 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar 2023-12-22T16:12:54Z | INFO | [ Complete ] dest=/src/weights-cache/61d61cadc695e415 size="186 MB" total_elapsed=0.742s url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar b'' Downloaded weights in 0.9362092018127441 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A <s0><s1> Simpsons character of a woman txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:07, 3.66it/s] 7%|▋ | 2/30 [00:00<00:07, 3.65it/s] 10%|█ | 3/30 [00:00<00:07, 3.65it/s] 13%|█▎ | 4/30 [00:01<00:07, 3.65it/s] 17%|█▋ | 5/30 [00:01<00:06, 3.65it/s] 20%|██ | 6/30 [00:01<00:06, 3.65it/s] 23%|██▎ | 7/30 [00:01<00:06, 3.65it/s] 27%|██▋ | 8/30 [00:02<00:06, 3.65it/s] 30%|███ | 9/30 [00:02<00:05, 3.66it/s] 33%|███▎ | 10/30 [00:02<00:05, 3.65it/s] 37%|███▋ | 11/30 [00:03<00:05, 3.65it/s] 40%|████ | 12/30 [00:03<00:04, 3.66it/s] 43%|████▎ | 13/30 [00:03<00:04, 3.66it/s] 47%|████▋ | 14/30 [00:03<00:04, 3.66it/s] 50%|█████ | 15/30 [00:04<00:04, 3.66it/s] 53%|█████▎ | 16/30 [00:04<00:03, 3.66it/s] 57%|█████▋ | 17/30 [00:04<00:03, 3.65it/s] 60%|██████ | 18/30 [00:04<00:03, 3.65it/s] 63%|██████▎ | 19/30 [00:05<00:03, 3.65it/s] 67%|██████▋ | 20/30 [00:05<00:02, 3.65it/s] 70%|███████ | 21/30 [00:05<00:02, 3.65it/s] 73%|███████▎ | 22/30 [00:06<00:02, 3.65it/s] 77%|███████▋ | 23/30 [00:06<00:01, 3.65it/s] 80%|████████ | 24/30 [00:06<00:01, 3.65it/s] 83%|████████▎ | 25/30 [00:06<00:01, 3.65it/s] 87%|████████▋ | 26/30 [00:07<00:01, 3.65it/s] 90%|█████████ | 27/30 [00:07<00:00, 3.65it/s] 93%|█████████▎| 28/30 [00:07<00:00, 3.64it/s] 97%|█████████▋| 29/30 [00:07<00:00, 3.64it/s] 100%|██████████| 30/30 [00:08<00:00, 3.64it/s] 100%|██████████| 30/30 [00:08<00:00, 3.65it/s]
Prediction
fofr/sdxl-simpsons-characters:f14fe2daaad569656058541c92fb199c8c59d6cbd085eb31192a8db8577a6931IDvquk5otbbftmsnk5pn7siojb6uStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 768
- height
- 768
- prompt
- A TOK Simpsons character of Einstein
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.4
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.9
- negative_prompt
- prompt_strength
- 0.95
- num_inference_steps
- 30
{ "width": 768, "height": 768, "prompt": "A TOK Simpsons character of Einstein", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.4, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "", "prompt_strength": 0.95, "num_inference_steps": 30 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-simpsons-characters:f14fe2daaad569656058541c92fb199c8c59d6cbd085eb31192a8db8577a6931", { input: { width: 768, height: 768, prompt: "A TOK Simpsons character of Einstein", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.4, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.9, negative_prompt: "", prompt_strength: 0.95, 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 fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-simpsons-characters:f14fe2daaad569656058541c92fb199c8c59d6cbd085eb31192a8db8577a6931", input={ "width": 768, "height": 768, "prompt": "A TOK Simpsons character of Einstein", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.4, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.9, "negative_prompt": "", "prompt_strength": 0.95, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-simpsons-characters 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": "f14fe2daaad569656058541c92fb199c8c59d6cbd085eb31192a8db8577a6931", "input": { "width": 768, "height": 768, "prompt": "A TOK Simpsons character of Einstein", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.4, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "", "prompt_strength": 0.95, "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/fofr/sdxl-simpsons-characters@sha256:f14fe2daaad569656058541c92fb199c8c59d6cbd085eb31192a8db8577a6931 \ -i 'width=768' \ -i 'height=768' \ -i 'prompt="A TOK Simpsons character of Einstein"' \ -i 'refine="expert_ensemble_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.4' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=false' \ -i 'high_noise_frac=0.9' \ -i 'negative_prompt=""' \ -i 'prompt_strength=0.95' \ -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/fofr/sdxl-simpsons-characters@sha256:f14fe2daaad569656058541c92fb199c8c59d6cbd085eb31192a8db8577a6931
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 768, "height": 768, "prompt": "A TOK Simpsons character of Einstein", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.4, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "", "prompt_strength": 0.95, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-22T16:01:56.473876Z", "created_at": "2023-12-22T16:01:16.955439Z", "data_removed": false, "error": null, "id": "vquk5otbbftmsnk5pn7siojb6u", "input": { "width": 768, "height": 768, "prompt": "A TOK Simpsons character of Einstein", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.4, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.9, "negative_prompt": "", "prompt_strength": 0.95, "num_inference_steps": 30 }, "logs": "Using seed: 33795\nEnsuring enough disk space...\nFree disk space: 1842877808640\nDownloading weights: https://replicate.delivery/pbxt/IXKWOSU7ujZWD9iecNF3neMPrXHvQyOm2SHGfh3GHlbCYsJkA/trained_model.tar\n2023-12-22T16:01:48Z | INFO | [ Initiating ] dest=/src/weights-cache/35612545502cd66b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/IXKWOSU7ujZWD9iecNF3neMPrXHvQyOm2SHGfh3GHlbCYsJkA/trained_model.tar\n2023-12-22T16:01:49Z | INFO | [ Complete ] dest=/src/weights-cache/35612545502cd66b size=\"186 MB\" total_elapsed=0.751s url=https://replicate.delivery/pbxt/IXKWOSU7ujZWD9iecNF3neMPrXHvQyOm2SHGfh3GHlbCYsJkA/trained_model.tar\nb''\nDownloaded weights in 0.9475414752960205 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A <s0><s1> Simpsons character of Einstein\ntxt2img mode\n 0%| | 0/27 [00:00<?, ?it/s]\n 4%|▎ | 1/27 [00:00<00:04, 6.20it/s]\n 7%|▋ | 2/27 [00:00<00:04, 6.20it/s]\n 11%|█ | 3/27 [00:00<00:03, 6.19it/s]\n 15%|█▍ | 4/27 [00:00<00:03, 6.19it/s]\n 19%|█▊ | 5/27 [00:00<00:03, 6.19it/s]\n 22%|██▏ | 6/27 [00:00<00:03, 6.20it/s]\n 26%|██▌ | 7/27 [00:01<00:03, 6.20it/s]\n 30%|██▉ | 8/27 [00:01<00:03, 6.19it/s]\n 33%|███▎ | 9/27 [00:01<00:02, 6.19it/s]\n 37%|███▋ | 10/27 [00:01<00:02, 6.19it/s]\n 41%|████ | 11/27 [00:01<00:02, 6.19it/s]\n 44%|████▍ | 12/27 [00:01<00:02, 6.19it/s]\n 48%|████▊ | 13/27 [00:02<00:02, 6.19it/s]\n 52%|█████▏ | 14/27 [00:02<00:02, 6.18it/s]\n 56%|█████▌ | 15/27 [00:02<00:01, 6.19it/s]\n 59%|█████▉ | 16/27 [00:02<00:01, 6.19it/s]\n 63%|██████▎ | 17/27 [00:02<00:01, 6.19it/s]\n 67%|██████▋ | 18/27 [00:02<00:01, 6.19it/s]\n 70%|███████ | 19/27 [00:03<00:01, 6.19it/s]\n 74%|███████▍ | 20/27 [00:03<00:01, 6.19it/s]\n 78%|███████▊ | 21/27 [00:03<00:00, 6.19it/s]\n 81%|████████▏ | 22/27 [00:03<00:00, 6.18it/s]\n 85%|████████▌ | 23/27 [00:03<00:00, 6.18it/s]\n 89%|████████▉ | 24/27 [00:03<00:00, 6.19it/s]\n 93%|█████████▎| 25/27 [00:04<00:00, 6.19it/s]\n 96%|█████████▋| 26/27 [00:04<00:00, 6.19it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.20it/s]\n100%|██████████| 27/27 [00:04<00:00, 6.19it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 6.92it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 7.40it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.56it/s]\n100%|██████████| 3/3 [00:00<00:00, 7.46it/s]", "metrics": { "predict_time": 7.657657, "total_time": 39.518437 }, "output": [ "https://replicate.delivery/pbxt/BHROBrfMRj0XIaxSfja0D1yG48NvIOVam1Sf3jcKUfdMPZTIB/out-0.png" ], "started_at": "2023-12-22T16:01:48.816219Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/vquk5otbbftmsnk5pn7siojb6u", "cancel": "https://api.replicate.com/v1/predictions/vquk5otbbftmsnk5pn7siojb6u/cancel" }, "version": "f14fe2daaad569656058541c92fb199c8c59d6cbd085eb31192a8db8577a6931" }
Generated inUsing seed: 33795 Ensuring enough disk space... Free disk space: 1842877808640 Downloading weights: https://replicate.delivery/pbxt/IXKWOSU7ujZWD9iecNF3neMPrXHvQyOm2SHGfh3GHlbCYsJkA/trained_model.tar 2023-12-22T16:01:48Z | INFO | [ Initiating ] dest=/src/weights-cache/35612545502cd66b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/IXKWOSU7ujZWD9iecNF3neMPrXHvQyOm2SHGfh3GHlbCYsJkA/trained_model.tar 2023-12-22T16:01:49Z | INFO | [ Complete ] dest=/src/weights-cache/35612545502cd66b size="186 MB" total_elapsed=0.751s url=https://replicate.delivery/pbxt/IXKWOSU7ujZWD9iecNF3neMPrXHvQyOm2SHGfh3GHlbCYsJkA/trained_model.tar b'' Downloaded weights in 0.9475414752960205 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A <s0><s1> Simpsons character of Einstein txt2img mode 0%| | 0/27 [00:00<?, ?it/s] 4%|▎ | 1/27 [00:00<00:04, 6.20it/s] 7%|▋ | 2/27 [00:00<00:04, 6.20it/s] 11%|█ | 3/27 [00:00<00:03, 6.19it/s] 15%|█▍ | 4/27 [00:00<00:03, 6.19it/s] 19%|█▊ | 5/27 [00:00<00:03, 6.19it/s] 22%|██▏ | 6/27 [00:00<00:03, 6.20it/s] 26%|██▌ | 7/27 [00:01<00:03, 6.20it/s] 30%|██▉ | 8/27 [00:01<00:03, 6.19it/s] 33%|███▎ | 9/27 [00:01<00:02, 6.19it/s] 37%|███▋ | 10/27 [00:01<00:02, 6.19it/s] 41%|████ | 11/27 [00:01<00:02, 6.19it/s] 44%|████▍ | 12/27 [00:01<00:02, 6.19it/s] 48%|████▊ | 13/27 [00:02<00:02, 6.19it/s] 52%|█████▏ | 14/27 [00:02<00:02, 6.18it/s] 56%|█████▌ | 15/27 [00:02<00:01, 6.19it/s] 59%|█████▉ | 16/27 [00:02<00:01, 6.19it/s] 63%|██████▎ | 17/27 [00:02<00:01, 6.19it/s] 67%|██████▋ | 18/27 [00:02<00:01, 6.19it/s] 70%|███████ | 19/27 [00:03<00:01, 6.19it/s] 74%|███████▍ | 20/27 [00:03<00:01, 6.19it/s] 78%|███████▊ | 21/27 [00:03<00:00, 6.19it/s] 81%|████████▏ | 22/27 [00:03<00:00, 6.18it/s] 85%|████████▌ | 23/27 [00:03<00:00, 6.18it/s] 89%|████████▉ | 24/27 [00:03<00:00, 6.19it/s] 93%|█████████▎| 25/27 [00:04<00:00, 6.19it/s] 96%|█████████▋| 26/27 [00:04<00:00, 6.19it/s] 100%|██████████| 27/27 [00:04<00:00, 6.20it/s] 100%|██████████| 27/27 [00:04<00:00, 6.19it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 6.92it/s] 67%|██████▋ | 2/3 [00:00<00:00, 7.40it/s] 100%|██████████| 3/3 [00:00<00:00, 7.56it/s] 100%|██████████| 3/3 [00:00<00:00, 7.46it/s]
Prediction
fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91IDbgyk533bj2rednaxhvuiouuflyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A TOK Simpsons character of Keanu Reeves
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- ugly, broken, distorted, artefacts, 3D, render, photography
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Keanu Reeves", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "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"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", { input: { width: 1024, height: 1024, prompt: "A TOK Simpsons character of Keanu Reeves", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.8, negative_prompt: "ugly, broken, distorted, artefacts, 3D, render, photography", 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 fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", input={ "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Keanu Reeves", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-simpsons-characters 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": "f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Keanu Reeves", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "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.
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/fofr/sdxl-simpsons-characters@sha256:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A TOK Simpsons character of Keanu Reeves"' \ -i 'refine="expert_ensemble_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=false' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="ugly, broken, distorted, artefacts, 3D, render, photography"' \ -i 'prompt_strength=0.8' \ -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/fofr/sdxl-simpsons-characters@sha256:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Keanu Reeves", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-22T16:14:22.321836Z", "created_at": "2023-12-22T16:14:01.589556Z", "data_removed": false, "error": null, "id": "bgyk533bj2rednaxhvuiouufly", "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Keanu Reeves", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 59539\nEnsuring enough disk space...\nFree disk space: 1796566224896\nDownloading weights: https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\n2023-12-22T16:14:05Z | INFO | [ Initiating ] dest=/src/weights-cache/61d61cadc695e415 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\n2023-12-22T16:14:12Z | INFO | [ Complete ] dest=/src/weights-cache/61d61cadc695e415 size=\"186 MB\" total_elapsed=6.848s url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\nb''\nDownloaded weights in 7.023523330688477 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A <s0><s1> Simpsons character of Keanu Reeves\ntxt2img mode\n 0%| | 0/23 [00:00<?, ?it/s]\n 4%|▍ | 1/23 [00:00<00:05, 3.68it/s]\n 9%|▊ | 2/23 [00:00<00:05, 3.67it/s]\n 13%|█▎ | 3/23 [00:00<00:05, 3.66it/s]\n 17%|█▋ | 4/23 [00:01<00:05, 3.66it/s]\n 22%|██▏ | 5/23 [00:01<00:04, 3.66it/s]\n 26%|██▌ | 6/23 [00:01<00:04, 3.67it/s]\n 30%|███ | 7/23 [00:01<00:04, 3.67it/s]\n 35%|███▍ | 8/23 [00:02<00:04, 3.67it/s]\n 39%|███▉ | 9/23 [00:02<00:03, 3.67it/s]\n 43%|████▎ | 10/23 [00:02<00:03, 3.67it/s]\n 48%|████▊ | 11/23 [00:02<00:03, 3.67it/s]\n 52%|█████▏ | 12/23 [00:03<00:02, 3.67it/s]\n 57%|█████▋ | 13/23 [00:03<00:02, 3.66it/s]\n 61%|██████ | 14/23 [00:03<00:02, 3.66it/s]\n 65%|██████▌ | 15/23 [00:04<00:02, 3.67it/s]\n 70%|██████▉ | 16/23 [00:04<00:01, 3.66it/s]\n 74%|███████▍ | 17/23 [00:04<00:01, 3.66it/s]\n 78%|███████▊ | 18/23 [00:04<00:01, 3.66it/s]\n 83%|████████▎ | 19/23 [00:05<00:01, 3.66it/s]\n 87%|████████▋ | 20/23 [00:05<00:00, 3.66it/s]\n 91%|█████████▏| 21/23 [00:05<00:00, 3.66it/s]\n 96%|█████████▌| 22/23 [00:06<00:00, 3.66it/s]\n100%|██████████| 23/23 [00:06<00:00, 3.66it/s]\n100%|██████████| 23/23 [00:06<00:00, 3.66it/s]\n 0%| | 0/7 [00:00<?, ?it/s]\n 14%|█▍ | 1/7 [00:00<00:01, 4.07it/s]\n 29%|██▊ | 2/7 [00:00<00:01, 4.19it/s]\n 43%|████▎ | 3/7 [00:00<00:00, 4.22it/s]\n 57%|█████▋ | 4/7 [00:00<00:00, 4.21it/s]\n 71%|███████▏ | 5/7 [00:01<00:00, 4.22it/s]\n 86%|████████▌ | 6/7 [00:01<00:00, 4.23it/s]\n100%|██████████| 7/7 [00:01<00:00, 4.23it/s]\n100%|██████████| 7/7 [00:01<00:00, 4.22it/s]", "metrics": { "predict_time": 16.590376, "total_time": 20.73228 }, "output": [ "https://replicate.delivery/pbxt/6Fxg96DtEf2KL6R4WoKEbs09Y6aCGpy7fgzhoLRFvRMdfsJkA/out-0.png" ], "started_at": "2023-12-22T16:14:05.731460Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/bgyk533bj2rednaxhvuiouufly", "cancel": "https://api.replicate.com/v1/predictions/bgyk533bj2rednaxhvuiouufly/cancel" }, "version": "f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91" }
Generated inUsing seed: 59539 Ensuring enough disk space... Free disk space: 1796566224896 Downloading weights: https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar 2023-12-22T16:14:05Z | INFO | [ Initiating ] dest=/src/weights-cache/61d61cadc695e415 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar 2023-12-22T16:14:12Z | INFO | [ Complete ] dest=/src/weights-cache/61d61cadc695e415 size="186 MB" total_elapsed=6.848s url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar b'' Downloaded weights in 7.023523330688477 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A <s0><s1> Simpsons character of Keanu Reeves txt2img mode 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:05, 3.68it/s] 9%|▊ | 2/23 [00:00<00:05, 3.67it/s] 13%|█▎ | 3/23 [00:00<00:05, 3.66it/s] 17%|█▋ | 4/23 [00:01<00:05, 3.66it/s] 22%|██▏ | 5/23 [00:01<00:04, 3.66it/s] 26%|██▌ | 6/23 [00:01<00:04, 3.67it/s] 30%|███ | 7/23 [00:01<00:04, 3.67it/s] 35%|███▍ | 8/23 [00:02<00:04, 3.67it/s] 39%|███▉ | 9/23 [00:02<00:03, 3.67it/s] 43%|████▎ | 10/23 [00:02<00:03, 3.67it/s] 48%|████▊ | 11/23 [00:02<00:03, 3.67it/s] 52%|█████▏ | 12/23 [00:03<00:02, 3.67it/s] 57%|█████▋ | 13/23 [00:03<00:02, 3.66it/s] 61%|██████ | 14/23 [00:03<00:02, 3.66it/s] 65%|██████▌ | 15/23 [00:04<00:02, 3.67it/s] 70%|██████▉ | 16/23 [00:04<00:01, 3.66it/s] 74%|███████▍ | 17/23 [00:04<00:01, 3.66it/s] 78%|███████▊ | 18/23 [00:04<00:01, 3.66it/s] 83%|████████▎ | 19/23 [00:05<00:01, 3.66it/s] 87%|████████▋ | 20/23 [00:05<00:00, 3.66it/s] 91%|█████████▏| 21/23 [00:05<00:00, 3.66it/s] 96%|█████████▌| 22/23 [00:06<00:00, 3.66it/s] 100%|██████████| 23/23 [00:06<00:00, 3.66it/s] 100%|██████████| 23/23 [00:06<00:00, 3.66it/s] 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:00<00:01, 4.07it/s] 29%|██▊ | 2/7 [00:00<00:01, 4.19it/s] 43%|████▎ | 3/7 [00:00<00:00, 4.22it/s] 57%|█████▋ | 4/7 [00:00<00:00, 4.21it/s] 71%|███████▏ | 5/7 [00:01<00:00, 4.22it/s] 86%|████████▌ | 6/7 [00:01<00:00, 4.23it/s] 100%|██████████| 7/7 [00:01<00:00, 4.23it/s] 100%|██████████| 7/7 [00:01<00:00, 4.22it/s]
Prediction
fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91IDq3fxk7lbzyvzsgt5zjlhfoifhaStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A TOK Simpsons character of Jean Luc Picard in starfleet uniform
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- ugly, broken, distorted, artefacts, 3D, render, photography
- prompt_strength
- 0.8
- num_inference_steps
- 30
{ "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Jean Luc Picard in starfleet uniform", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "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"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", { input: { width: 1024, height: 1024, prompt: "A TOK Simpsons character of Jean Luc Picard in starfleet uniform", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.8, negative_prompt: "ugly, broken, distorted, artefacts, 3D, render, photography", 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 fofr/sdxl-simpsons-characters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-simpsons-characters:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", input={ "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Jean Luc Picard in starfleet uniform", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run fofr/sdxl-simpsons-characters 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": "f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91", "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Jean Luc Picard in starfleet uniform", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "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.
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/fofr/sdxl-simpsons-characters@sha256:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91 \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A TOK Simpsons character of Jean Luc Picard in starfleet uniform"' \ -i 'refine="expert_ensemble_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=1' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=false' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="ugly, broken, distorted, artefacts, 3D, render, photography"' \ -i 'prompt_strength=0.8' \ -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/fofr/sdxl-simpsons-characters@sha256:f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Jean Luc Picard in starfleet uniform", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-12-22T16:26:54.789256Z", "created_at": "2023-12-22T16:26:40.077287Z", "data_removed": false, "error": null, "id": "q3fxk7lbzyvzsgt5zjlhfoifha", "input": { "width": 1024, "height": 1024, "prompt": "A TOK Simpsons character of Jean Luc Picard in starfleet uniform", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.8, "negative_prompt": "ugly, broken, distorted, artefacts, 3D, render, photography", "prompt_strength": 0.8, "num_inference_steps": 30 }, "logs": "Using seed: 18141\nEnsuring enough disk space...\nFree disk space: 2029064146944\nDownloading weights: https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\n2023-12-22T16:26:43Z | INFO | [ Initiating ] dest=/src/weights-cache/61d61cadc695e415 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\n2023-12-22T16:26:44Z | INFO | [ Complete ] dest=/src/weights-cache/61d61cadc695e415 size=\"186 MB\" total_elapsed=0.462s url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar\nb''\nDownloaded weights in 0.5937182903289795 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A <s0><s1> Simpsons character of Jean Luc Picard in starfleet uniform\ntxt2img mode\n 0%| | 0/23 [00:00<?, ?it/s]\n 4%|▍ | 1/23 [00:00<00:06, 3.63it/s]\n 9%|▊ | 2/23 [00:00<00:05, 3.62it/s]\n 13%|█▎ | 3/23 [00:00<00:05, 3.61it/s]\n 17%|█▋ | 4/23 [00:01<00:05, 3.61it/s]\n 22%|██▏ | 5/23 [00:01<00:04, 3.61it/s]\n 26%|██▌ | 6/23 [00:01<00:04, 3.61it/s]\n 30%|███ | 7/23 [00:01<00:04, 3.61it/s]\n 35%|███▍ | 8/23 [00:02<00:04, 3.61it/s]\n 39%|███▉ | 9/23 [00:02<00:03, 3.61it/s]\n 43%|████▎ | 10/23 [00:02<00:03, 3.61it/s]\n 48%|████▊ | 11/23 [00:03<00:03, 3.60it/s]\n 52%|█████▏ | 12/23 [00:03<00:03, 3.61it/s]\n 57%|█████▋ | 13/23 [00:03<00:02, 3.60it/s]\n 61%|██████ | 14/23 [00:03<00:02, 3.60it/s]\n 65%|██████▌ | 15/23 [00:04<00:02, 3.60it/s]\n 70%|██████▉ | 16/23 [00:04<00:01, 3.61it/s]\n 74%|███████▍ | 17/23 [00:04<00:01, 3.60it/s]\n 78%|███████▊ | 18/23 [00:04<00:01, 3.60it/s]\n 83%|████████▎ | 19/23 [00:05<00:01, 3.60it/s]\n 87%|████████▋ | 20/23 [00:05<00:00, 3.60it/s]\n 91%|█████████▏| 21/23 [00:05<00:00, 3.59it/s]\n 96%|█████████▌| 22/23 [00:06<00:00, 3.56it/s]\n100%|██████████| 23/23 [00:06<00:00, 3.57it/s]\n100%|██████████| 23/23 [00:06<00:00, 3.60it/s]\n 0%| | 0/7 [00:00<?, ?it/s]\n 14%|█▍ | 1/7 [00:00<00:01, 3.96it/s]\n 29%|██▊ | 2/7 [00:00<00:01, 4.08it/s]\n 43%|████▎ | 3/7 [00:00<00:00, 4.13it/s]\n 57%|█████▋ | 4/7 [00:00<00:00, 4.14it/s]\n 71%|███████▏ | 5/7 [00:01<00:00, 4.15it/s]\n 86%|████████▌ | 6/7 [00:01<00:00, 4.16it/s]\n100%|██████████| 7/7 [00:01<00:00, 4.16it/s]\n100%|██████████| 7/7 [00:01<00:00, 4.14it/s]", "metrics": { "predict_time": 11.122483, "total_time": 14.711969 }, "output": [ "https://replicate.delivery/pbxt/ZtcZALxzW3IsAJB4gTi9mOAw5lTHg4hGMeQrieVQnruNr2ESA/out-0.png" ], "started_at": "2023-12-22T16:26:43.666773Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/q3fxk7lbzyvzsgt5zjlhfoifha", "cancel": "https://api.replicate.com/v1/predictions/q3fxk7lbzyvzsgt5zjlhfoifha/cancel" }, "version": "f4d36a72b43ea2fd511cab0afb32539955ee5b28b65c8e3fb7d8abd254be8e91" }
Generated inUsing seed: 18141 Ensuring enough disk space... Free disk space: 2029064146944 Downloading weights: https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar 2023-12-22T16:26:43Z | INFO | [ Initiating ] dest=/src/weights-cache/61d61cadc695e415 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar 2023-12-22T16:26:44Z | INFO | [ Complete ] dest=/src/weights-cache/61d61cadc695e415 size="186 MB" total_elapsed=0.462s url=https://replicate.delivery/pbxt/fNgClbeGdYulIURATUep5GC1z82eubbtyEBCribWU7BljZTIB/trained_model.tar b'' Downloaded weights in 0.5937182903289795 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: A <s0><s1> Simpsons character of Jean Luc Picard in starfleet uniform txt2img mode 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:06, 3.63it/s] 9%|▊ | 2/23 [00:00<00:05, 3.62it/s] 13%|█▎ | 3/23 [00:00<00:05, 3.61it/s] 17%|█▋ | 4/23 [00:01<00:05, 3.61it/s] 22%|██▏ | 5/23 [00:01<00:04, 3.61it/s] 26%|██▌ | 6/23 [00:01<00:04, 3.61it/s] 30%|███ | 7/23 [00:01<00:04, 3.61it/s] 35%|███▍ | 8/23 [00:02<00:04, 3.61it/s] 39%|███▉ | 9/23 [00:02<00:03, 3.61it/s] 43%|████▎ | 10/23 [00:02<00:03, 3.61it/s] 48%|████▊ | 11/23 [00:03<00:03, 3.60it/s] 52%|█████▏ | 12/23 [00:03<00:03, 3.61it/s] 57%|█████▋ | 13/23 [00:03<00:02, 3.60it/s] 61%|██████ | 14/23 [00:03<00:02, 3.60it/s] 65%|██████▌ | 15/23 [00:04<00:02, 3.60it/s] 70%|██████▉ | 16/23 [00:04<00:01, 3.61it/s] 74%|███████▍ | 17/23 [00:04<00:01, 3.60it/s] 78%|███████▊ | 18/23 [00:04<00:01, 3.60it/s] 83%|████████▎ | 19/23 [00:05<00:01, 3.60it/s] 87%|████████▋ | 20/23 [00:05<00:00, 3.60it/s] 91%|█████████▏| 21/23 [00:05<00:00, 3.59it/s] 96%|█████████▌| 22/23 [00:06<00:00, 3.56it/s] 100%|██████████| 23/23 [00:06<00:00, 3.57it/s] 100%|██████████| 23/23 [00:06<00:00, 3.60it/s] 0%| | 0/7 [00:00<?, ?it/s] 14%|█▍ | 1/7 [00:00<00:01, 3.96it/s] 29%|██▊ | 2/7 [00:00<00:01, 4.08it/s] 43%|████▎ | 3/7 [00:00<00:00, 4.13it/s] 57%|█████▋ | 4/7 [00:00<00:00, 4.14it/s] 71%|███████▏ | 5/7 [00:01<00:00, 4.15it/s] 86%|████████▌ | 6/7 [00:01<00:00, 4.16it/s] 100%|██████████| 7/7 [00:01<00:00, 4.16it/s] 100%|██████████| 7/7 [00:01<00:00, 4.14it/s]
Want to make some of these yourself?
Run this model