fofr
/
sdxl-pans-labyrinth
An SDXL fine-tune based on Pan's Labyrinth
- Public
- 298 runs
-
L40S
- SDXL fine-tune
Prediction
fofr/sdxl-pans-labyrinth:ed76ae34IDwf3hyodbuyve2gs4cgfvum7nsmStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- A film still of a room in the style of TOK
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- underexposed
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "A film still of a room in the style of TOK", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-pans-labyrinth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-pans-labyrinth:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", { input: { width: 1024, height: 1024, prompt: "A film still of a room in the style of TOK", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "underexposed", prompt_strength: 0.8, num_inference_steps: 50 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run fofr/sdxl-pans-labyrinth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-pans-labyrinth:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", input={ "width": 1024, "height": 1024, "prompt": "A film still of a room in the style of TOK", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run fofr/sdxl-pans-labyrinth 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": "ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", "input": { "width": 1024, "height": 1024, "prompt": "A film still of a room in the style of TOK", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run fofr/sdxl-pans-labyrinth using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/fofr/sdxl-pans-labyrinth@sha256:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="A film still of a room in the style of TOK"' \ -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=0.95' \ -i 'negative_prompt="underexposed"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'
To learn more, take a look at the Cog documentation.
Pull and run fofr/sdxl-pans-labyrinth using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/fofr/sdxl-pans-labyrinth@sha256:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "A film still of a room in the style of TOK", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2023-09-01T22:19:53.671859Z", "created_at": "2023-09-01T22:19:39.083653Z", "data_removed": false, "error": null, "id": "wf3hyodbuyve2gs4cgfvum7nsm", "input": { "width": 1024, "height": 1024, "prompt": "A film still of a room in the style of TOK", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 48578\nPrompt: A film still of a room in the style of <s0><s1>\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:00<00:12, 3.73it/s]\n 4%|▍ | 2/47 [00:00<00:12, 3.72it/s]\n 6%|▋ | 3/47 [00:00<00:11, 3.71it/s]\n 9%|▊ | 4/47 [00:01<00:11, 3.71it/s]\n 11%|█ | 5/47 [00:01<00:11, 3.71it/s]\n 13%|█▎ | 6/47 [00:01<00:11, 3.71it/s]\n 15%|█▍ | 7/47 [00:01<00:10, 3.70it/s]\n 17%|█▋ | 8/47 [00:02<00:10, 3.70it/s]\n 19%|█▉ | 9/47 [00:02<00:10, 3.70it/s]\n 21%|██▏ | 10/47 [00:02<00:09, 3.71it/s]\n 23%|██▎ | 11/47 [00:02<00:09, 3.71it/s]\n 26%|██▌ | 12/47 [00:03<00:09, 3.71it/s]\n 28%|██▊ | 13/47 [00:03<00:09, 3.71it/s]\n 30%|██▉ | 14/47 [00:03<00:08, 3.68it/s]\n 32%|███▏ | 15/47 [00:04<00:08, 3.68it/s]\n 34%|███▍ | 16/47 [00:04<00:08, 3.69it/s]\n 36%|███▌ | 17/47 [00:04<00:08, 3.70it/s]\n 38%|███▊ | 18/47 [00:04<00:07, 3.70it/s]\n 40%|████ | 19/47 [00:05<00:07, 3.71it/s]\n 43%|████▎ | 20/47 [00:05<00:07, 3.71it/s]\n 45%|████▍ | 21/47 [00:05<00:07, 3.71it/s]\n 47%|████▋ | 22/47 [00:05<00:06, 3.71it/s]\n 49%|████▉ | 23/47 [00:06<00:06, 3.71it/s]\n 51%|█████ | 24/47 [00:06<00:06, 3.72it/s]\n 53%|█████▎ | 25/47 [00:06<00:05, 3.71it/s]\n 55%|█████▌ | 26/47 [00:07<00:05, 3.72it/s]\n 57%|█████▋ | 27/47 [00:07<00:05, 3.72it/s]\n 60%|█████▉ | 28/47 [00:07<00:05, 3.72it/s]\n 62%|██████▏ | 29/47 [00:07<00:04, 3.72it/s]\n 64%|██████▍ | 30/47 [00:08<00:04, 3.71it/s]\n 66%|██████▌ | 31/47 [00:08<00:04, 3.72it/s]\n 68%|██████▊ | 32/47 [00:08<00:04, 3.72it/s]\n 70%|███████ | 33/47 [00:08<00:03, 3.71it/s]\n 72%|███████▏ | 34/47 [00:09<00:03, 3.71it/s]\n 74%|███████▍ | 35/47 [00:09<00:03, 3.72it/s]\n 77%|███████▋ | 36/47 [00:09<00:02, 3.71it/s]\n 79%|███████▊ | 37/47 [00:09<00:02, 3.71it/s]\n 81%|████████ | 38/47 [00:10<00:02, 3.71it/s]\n 83%|████████▎ | 39/47 [00:10<00:02, 3.71it/s]\n 85%|████████▌ | 40/47 [00:10<00:01, 3.71it/s]\n 87%|████████▋ | 41/47 [00:11<00:01, 3.71it/s]\n 89%|████████▉ | 42/47 [00:11<00:01, 3.71it/s]\n 91%|█████████▏| 43/47 [00:11<00:01, 3.71it/s]\n 94%|█████████▎| 44/47 [00:11<00:00, 3.71it/s]\n 96%|█████████▌| 45/47 [00:12<00:00, 3.71it/s]\n 98%|█████████▊| 46/47 [00:12<00:00, 3.71it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.71it/s]\n100%|██████████| 47/47 [00:12<00:00, 3.71it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 4.37it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 4.36it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.35it/s]\n100%|██████████| 3/3 [00:00<00:00, 4.36it/s]", "metrics": { "predict_time": 14.613676, "total_time": 14.588206 }, "output": [ "https://pbxt.replicate.delivery/CpiNLF1vLhJ0FFIy0YzLzD5yxAizzGfR1QGQGNewT4sJWBgRA/out-0.png" ], "started_at": "2023-09-01T22:19:39.058183Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/wf3hyodbuyve2gs4cgfvum7nsm", "cancel": "https://api.replicate.com/v1/predictions/wf3hyodbuyve2gs4cgfvum7nsm/cancel" }, "version": "ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a" }
Generated inUsing seed: 48578 Prompt: A film still of a room in the style of <s0><s1> txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:12, 3.73it/s] 4%|▍ | 2/47 [00:00<00:12, 3.72it/s] 6%|▋ | 3/47 [00:00<00:11, 3.71it/s] 9%|▊ | 4/47 [00:01<00:11, 3.71it/s] 11%|█ | 5/47 [00:01<00:11, 3.71it/s] 13%|█▎ | 6/47 [00:01<00:11, 3.71it/s] 15%|█▍ | 7/47 [00:01<00:10, 3.70it/s] 17%|█▋ | 8/47 [00:02<00:10, 3.70it/s] 19%|█▉ | 9/47 [00:02<00:10, 3.70it/s] 21%|██▏ | 10/47 [00:02<00:09, 3.71it/s] 23%|██▎ | 11/47 [00:02<00:09, 3.71it/s] 26%|██▌ | 12/47 [00:03<00:09, 3.71it/s] 28%|██▊ | 13/47 [00:03<00:09, 3.71it/s] 30%|██▉ | 14/47 [00:03<00:08, 3.68it/s] 32%|███▏ | 15/47 [00:04<00:08, 3.68it/s] 34%|███▍ | 16/47 [00:04<00:08, 3.69it/s] 36%|███▌ | 17/47 [00:04<00:08, 3.70it/s] 38%|███▊ | 18/47 [00:04<00:07, 3.70it/s] 40%|████ | 19/47 [00:05<00:07, 3.71it/s] 43%|████▎ | 20/47 [00:05<00:07, 3.71it/s] 45%|████▍ | 21/47 [00:05<00:07, 3.71it/s] 47%|████▋ | 22/47 [00:05<00:06, 3.71it/s] 49%|████▉ | 23/47 [00:06<00:06, 3.71it/s] 51%|█████ | 24/47 [00:06<00:06, 3.72it/s] 53%|█████▎ | 25/47 [00:06<00:05, 3.71it/s] 55%|█████▌ | 26/47 [00:07<00:05, 3.72it/s] 57%|█████▋ | 27/47 [00:07<00:05, 3.72it/s] 60%|█████▉ | 28/47 [00:07<00:05, 3.72it/s] 62%|██████▏ | 29/47 [00:07<00:04, 3.72it/s] 64%|██████▍ | 30/47 [00:08<00:04, 3.71it/s] 66%|██████▌ | 31/47 [00:08<00:04, 3.72it/s] 68%|██████▊ | 32/47 [00:08<00:04, 3.72it/s] 70%|███████ | 33/47 [00:08<00:03, 3.71it/s] 72%|███████▏ | 34/47 [00:09<00:03, 3.71it/s] 74%|███████▍ | 35/47 [00:09<00:03, 3.72it/s] 77%|███████▋ | 36/47 [00:09<00:02, 3.71it/s] 79%|███████▊ | 37/47 [00:09<00:02, 3.71it/s] 81%|████████ | 38/47 [00:10<00:02, 3.71it/s] 83%|████████▎ | 39/47 [00:10<00:02, 3.71it/s] 85%|████████▌ | 40/47 [00:10<00:01, 3.71it/s] 87%|████████▋ | 41/47 [00:11<00:01, 3.71it/s] 89%|████████▉ | 42/47 [00:11<00:01, 3.71it/s] 91%|█████████▏| 43/47 [00:11<00:01, 3.71it/s] 94%|█████████▎| 44/47 [00:11<00:00, 3.71it/s] 96%|█████████▌| 45/47 [00:12<00:00, 3.71it/s] 98%|█████████▊| 46/47 [00:12<00:00, 3.71it/s] 100%|██████████| 47/47 [00:12<00:00, 3.71it/s] 100%|██████████| 47/47 [00:12<00:00, 3.71it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 4.37it/s] 67%|██████▋ | 2/3 [00:00<00:00, 4.36it/s] 100%|██████████| 3/3 [00:00<00:00, 4.35it/s] 100%|██████████| 3/3 [00:00<00:00, 4.36it/s]
Prediction
fofr/sdxl-pans-labyrinth:ed76ae34IDyn6dfcdbgphmahlujx65qvkoduStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1152
- height
- 768
- prompt
- A photo of a creepy monster with black ooze in a bathroom
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- underexposed
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1152, "height": 768, "prompt": "A photo of a creepy monster with black ooze in a bathroom", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-pans-labyrinth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-pans-labyrinth:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", { input: { width: 1152, height: 768, prompt: "A photo of a creepy monster with black ooze in a bathroom", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "underexposed", prompt_strength: 0.8, num_inference_steps: 50 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run fofr/sdxl-pans-labyrinth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-pans-labyrinth:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", input={ "width": 1152, "height": 768, "prompt": "A photo of a creepy monster with black ooze in a bathroom", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run fofr/sdxl-pans-labyrinth 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": "ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", "input": { "width": 1152, "height": 768, "prompt": "A photo of a creepy monster with black ooze in a bathroom", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run fofr/sdxl-pans-labyrinth using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/fofr/sdxl-pans-labyrinth@sha256:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a \ -i 'width=1152' \ -i 'height=768' \ -i 'prompt="A photo of a creepy monster with black ooze in a bathroom"' \ -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=0.95' \ -i 'negative_prompt="underexposed"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'
To learn more, take a look at the Cog documentation.
Pull and run fofr/sdxl-pans-labyrinth using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/fofr/sdxl-pans-labyrinth@sha256:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1152, "height": 768, "prompt": "A photo of a creepy monster with black ooze in a bathroom", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2023-09-01T22:40:30.520025Z", "created_at": "2023-09-01T22:40:17.966429Z", "data_removed": false, "error": null, "id": "yn6dfcdbgphmahlujx65qvkodu", "input": { "width": 1152, "height": 768, "prompt": "A photo of a creepy monster with black ooze in a bathroom", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 7809\nPrompt: A photo of a creepy monster with black ooze in a bathroom\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:00<00:10, 4.40it/s]\n 4%|▍ | 2/47 [00:00<00:10, 4.38it/s]\n 6%|▋ | 3/47 [00:00<00:10, 4.36it/s]\n 9%|▊ | 4/47 [00:00<00:09, 4.35it/s]\n 11%|█ | 5/47 [00:01<00:09, 4.34it/s]\n 13%|█▎ | 6/47 [00:01<00:09, 4.35it/s]\n 15%|█▍ | 7/47 [00:01<00:09, 4.34it/s]\n 17%|█▋ | 8/47 [00:01<00:08, 4.34it/s]\n 19%|█▉ | 9/47 [00:02<00:08, 4.34it/s]\n 21%|██▏ | 10/47 [00:02<00:08, 4.34it/s]\n 23%|██▎ | 11/47 [00:02<00:08, 4.34it/s]\n 26%|██▌ | 12/47 [00:02<00:08, 4.34it/s]\n 28%|██▊ | 13/47 [00:02<00:07, 4.34it/s]\n 30%|██▉ | 14/47 [00:03<00:07, 4.34it/s]\n 32%|███▏ | 15/47 [00:03<00:07, 4.34it/s]\n 34%|███▍ | 16/47 [00:03<00:07, 4.34it/s]\n 36%|███▌ | 17/47 [00:03<00:06, 4.34it/s]\n 38%|███▊ | 18/47 [00:04<00:06, 4.34it/s]\n 40%|████ | 19/47 [00:04<00:06, 4.34it/s]\n 43%|████▎ | 20/47 [00:04<00:06, 4.34it/s]\n 45%|████▍ | 21/47 [00:04<00:05, 4.35it/s]\n 47%|████▋ | 22/47 [00:05<00:05, 4.35it/s]\n 49%|████▉ | 23/47 [00:05<00:05, 4.35it/s]\n 51%|█████ | 24/47 [00:05<00:05, 4.36it/s]\n 53%|█████▎ | 25/47 [00:05<00:05, 4.35it/s]\n 55%|█████▌ | 26/47 [00:05<00:04, 4.36it/s]\n 57%|█████▋ | 27/47 [00:06<00:04, 4.35it/s]\n 60%|█████▉ | 28/47 [00:06<00:04, 4.36it/s]\n 62%|██████▏ | 29/47 [00:06<00:04, 4.36it/s]\n 64%|██████▍ | 30/47 [00:06<00:03, 4.36it/s]\n 66%|██████▌ | 31/47 [00:07<00:03, 4.36it/s]\n 68%|██████▊ | 32/47 [00:07<00:03, 4.36it/s]\n 70%|███████ | 33/47 [00:07<00:03, 4.36it/s]\n 72%|███████▏ | 34/47 [00:07<00:02, 4.36it/s]\n 74%|███████▍ | 35/47 [00:08<00:02, 4.36it/s]\n 77%|███████▋ | 36/47 [00:08<00:02, 4.36it/s]\n 79%|███████▊ | 37/47 [00:08<00:02, 4.36it/s]\n 81%|████████ | 38/47 [00:08<00:02, 4.36it/s]\n 83%|████████▎ | 39/47 [00:08<00:01, 4.36it/s]\n 85%|████████▌ | 40/47 [00:09<00:01, 4.35it/s]\n 87%|████████▋ | 41/47 [00:09<00:01, 4.35it/s]\n 89%|████████▉ | 42/47 [00:09<00:01, 4.36it/s]\n 91%|█████████▏| 43/47 [00:09<00:00, 4.36it/s]\n 94%|█████████▎| 44/47 [00:10<00:00, 4.36it/s]\n 96%|█████████▌| 45/47 [00:10<00:00, 4.35it/s]\n 98%|█████████▊| 46/47 [00:10<00:00, 4.35it/s]\n100%|██████████| 47/47 [00:10<00:00, 4.35it/s]\n100%|██████████| 47/47 [00:10<00:00, 4.35it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 5.67it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 5.63it/s]\n100%|██████████| 3/3 [00:00<00:00, 5.61it/s]\n100%|██████████| 3/3 [00:00<00:00, 5.62it/s]", "metrics": { "predict_time": 12.575549, "total_time": 12.553596 }, "output": [ "https://pbxt.replicate.delivery/gRwQmcLNOCI0ONsItLeeZa6KX6gkGSYt6HiSXvxNIkTeSDAjA/out-0.png" ], "started_at": "2023-09-01T22:40:17.944476Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/yn6dfcdbgphmahlujx65qvkodu", "cancel": "https://api.replicate.com/v1/predictions/yn6dfcdbgphmahlujx65qvkodu/cancel" }, "version": "ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a" }
Generated inUsing seed: 7809 Prompt: A photo of a creepy monster with black ooze in a bathroom txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:10, 4.40it/s] 4%|▍ | 2/47 [00:00<00:10, 4.38it/s] 6%|▋ | 3/47 [00:00<00:10, 4.36it/s] 9%|▊ | 4/47 [00:00<00:09, 4.35it/s] 11%|█ | 5/47 [00:01<00:09, 4.34it/s] 13%|█▎ | 6/47 [00:01<00:09, 4.35it/s] 15%|█▍ | 7/47 [00:01<00:09, 4.34it/s] 17%|█▋ | 8/47 [00:01<00:08, 4.34it/s] 19%|█▉ | 9/47 [00:02<00:08, 4.34it/s] 21%|██▏ | 10/47 [00:02<00:08, 4.34it/s] 23%|██▎ | 11/47 [00:02<00:08, 4.34it/s] 26%|██▌ | 12/47 [00:02<00:08, 4.34it/s] 28%|██▊ | 13/47 [00:02<00:07, 4.34it/s] 30%|██▉ | 14/47 [00:03<00:07, 4.34it/s] 32%|███▏ | 15/47 [00:03<00:07, 4.34it/s] 34%|███▍ | 16/47 [00:03<00:07, 4.34it/s] 36%|███▌ | 17/47 [00:03<00:06, 4.34it/s] 38%|███▊ | 18/47 [00:04<00:06, 4.34it/s] 40%|████ | 19/47 [00:04<00:06, 4.34it/s] 43%|████▎ | 20/47 [00:04<00:06, 4.34it/s] 45%|████▍ | 21/47 [00:04<00:05, 4.35it/s] 47%|████▋ | 22/47 [00:05<00:05, 4.35it/s] 49%|████▉ | 23/47 [00:05<00:05, 4.35it/s] 51%|█████ | 24/47 [00:05<00:05, 4.36it/s] 53%|█████▎ | 25/47 [00:05<00:05, 4.35it/s] 55%|█████▌ | 26/47 [00:05<00:04, 4.36it/s] 57%|█████▋ | 27/47 [00:06<00:04, 4.35it/s] 60%|█████▉ | 28/47 [00:06<00:04, 4.36it/s] 62%|██████▏ | 29/47 [00:06<00:04, 4.36it/s] 64%|██████▍ | 30/47 [00:06<00:03, 4.36it/s] 66%|██████▌ | 31/47 [00:07<00:03, 4.36it/s] 68%|██████▊ | 32/47 [00:07<00:03, 4.36it/s] 70%|███████ | 33/47 [00:07<00:03, 4.36it/s] 72%|███████▏ | 34/47 [00:07<00:02, 4.36it/s] 74%|███████▍ | 35/47 [00:08<00:02, 4.36it/s] 77%|███████▋ | 36/47 [00:08<00:02, 4.36it/s] 79%|███████▊ | 37/47 [00:08<00:02, 4.36it/s] 81%|████████ | 38/47 [00:08<00:02, 4.36it/s] 83%|████████▎ | 39/47 [00:08<00:01, 4.36it/s] 85%|████████▌ | 40/47 [00:09<00:01, 4.35it/s] 87%|████████▋ | 41/47 [00:09<00:01, 4.35it/s] 89%|████████▉ | 42/47 [00:09<00:01, 4.36it/s] 91%|█████████▏| 43/47 [00:09<00:00, 4.36it/s] 94%|█████████▎| 44/47 [00:10<00:00, 4.36it/s] 96%|█████████▌| 45/47 [00:10<00:00, 4.35it/s] 98%|█████████▊| 46/47 [00:10<00:00, 4.35it/s] 100%|██████████| 47/47 [00:10<00:00, 4.35it/s] 100%|██████████| 47/47 [00:10<00:00, 4.35it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 5.67it/s] 67%|██████▋ | 2/3 [00:00<00:00, 5.63it/s] 100%|██████████| 3/3 [00:00<00:00, 5.61it/s] 100%|██████████| 3/3 [00:00<00:00, 5.62it/s]
Prediction
fofr/sdxl-pans-labyrinth:ed76ae34IDelp5ytdbwzazyan4icerwlr43eStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1152
- height
- 768
- prompt
- In the style of TOK, a photo of a creepy cat
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.95
- negative_prompt
- underexposed
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1152, "height": 768, "prompt": "In the style of TOK, a photo of a creepy cat", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 }
npm install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import and set up the clientimport Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run fofr/sdxl-pans-labyrinth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "fofr/sdxl-pans-labyrinth:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", { input: { width: 1152, height: 768, prompt: "In the style of TOK, a photo of a creepy cat", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: false, high_noise_frac: 0.95, negative_prompt: "underexposed", prompt_strength: 0.8, num_inference_steps: 50 } } ); console.log(output);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Import the clientimport replicate
Run fofr/sdxl-pans-labyrinth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "fofr/sdxl-pans-labyrinth:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", input={ "width": 1152, "height": 768, "prompt": "In the style of TOK, a photo of a creepy cat", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": False, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Set theREPLICATE_API_TOKEN
environment variableexport REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run fofr/sdxl-pans-labyrinth 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": "ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a", "input": { "width": 1152, "height": 768, "prompt": "In the style of TOK, a photo of a creepy cat", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Install Cogbrew install cog
If you don’t have Homebrew, there are other installation options available.
Pull and run fofr/sdxl-pans-labyrinth using Cog (this will download the full model and run it in your local environment):
cog predict r8.im/fofr/sdxl-pans-labyrinth@sha256:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a \ -i 'width=1152' \ -i 'height=768' \ -i 'prompt="In the style of TOK, a photo of a creepy cat"' \ -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=0.95' \ -i 'negative_prompt="underexposed"' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'
To learn more, take a look at the Cog documentation.
Pull and run fofr/sdxl-pans-labyrinth using Docker (this will download the full model and run it in your local environment):
docker run -d -p 5000:5000 --gpus=all r8.im/fofr/sdxl-pans-labyrinth@sha256:ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1152, "height": 768, "prompt": "In the style of TOK, a photo of a creepy cat", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictions
Output
{ "completed_at": "2023-09-01T22:46:47.083041Z", "created_at": "2023-09-01T22:46:34.472400Z", "data_removed": false, "error": null, "id": "elp5ytdbwzazyan4icerwlr43e", "input": { "width": 1152, "height": 768, "prompt": "In the style of TOK, a photo of a creepy cat", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": false, "high_noise_frac": 0.95, "negative_prompt": "underexposed", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 29752\nPrompt: In the style of <s0><s1>, a photo of a creepy cat\ntxt2img mode\n 0%| | 0/47 [00:00<?, ?it/s]\n 2%|▏ | 1/47 [00:00<00:10, 4.33it/s]\n 4%|▍ | 2/47 [00:00<00:10, 4.33it/s]\n 6%|▋ | 3/47 [00:00<00:10, 4.33it/s]\n 9%|▊ | 4/47 [00:00<00:09, 4.33it/s]\n 11%|█ | 5/47 [00:01<00:09, 4.33it/s]\n 13%|█▎ | 6/47 [00:01<00:09, 4.33it/s]\n 15%|█▍ | 7/47 [00:01<00:09, 4.33it/s]\n 17%|█▋ | 8/47 [00:01<00:09, 4.33it/s]\n 19%|█▉ | 9/47 [00:02<00:08, 4.32it/s]\n 21%|██▏ | 10/47 [00:02<00:08, 4.32it/s]\n 23%|██▎ | 11/47 [00:02<00:08, 4.32it/s]\n 26%|██▌ | 12/47 [00:02<00:08, 4.32it/s]\n 28%|██▊ | 13/47 [00:03<00:07, 4.32it/s]\n 30%|██▉ | 14/47 [00:03<00:07, 4.32it/s]\n 32%|███▏ | 15/47 [00:03<00:07, 4.31it/s]\n 34%|███▍ | 16/47 [00:03<00:07, 4.31it/s]\n 36%|███▌ | 17/47 [00:03<00:06, 4.31it/s]\n 38%|███▊ | 18/47 [00:04<00:06, 4.31it/s]\n 40%|████ | 19/47 [00:04<00:06, 4.31it/s]\n 43%|████▎ | 20/47 [00:04<00:06, 4.31it/s]\n 45%|████▍ | 21/47 [00:04<00:06, 4.31it/s]\n 47%|████▋ | 22/47 [00:05<00:05, 4.31it/s]\n 49%|████▉ | 23/47 [00:05<00:05, 4.31it/s]\n 51%|█████ | 24/47 [00:05<00:05, 4.31it/s]\n 53%|█████▎ | 25/47 [00:05<00:05, 4.31it/s]\n 55%|█████▌ | 26/47 [00:06<00:04, 4.30it/s]\n 57%|█████▋ | 27/47 [00:06<00:04, 4.31it/s]\n 60%|█████▉ | 28/47 [00:06<00:04, 4.31it/s]\n 62%|██████▏ | 29/47 [00:06<00:04, 4.31it/s]\n 64%|██████▍ | 30/47 [00:06<00:03, 4.30it/s]\n 66%|██████▌ | 31/47 [00:07<00:03, 4.30it/s]\n 68%|██████▊ | 32/47 [00:07<00:03, 4.30it/s]\n 70%|███████ | 33/47 [00:07<00:03, 4.30it/s]\n 72%|███████▏ | 34/47 [00:07<00:03, 4.30it/s]\n 74%|███████▍ | 35/47 [00:08<00:02, 4.30it/s]\n 77%|███████▋ | 36/47 [00:08<00:02, 4.30it/s]\n 79%|███████▊ | 37/47 [00:08<00:02, 4.30it/s]\n 81%|████████ | 38/47 [00:08<00:02, 4.30it/s]\n 83%|████████▎ | 39/47 [00:09<00:01, 4.30it/s]\n 85%|████████▌ | 40/47 [00:09<00:01, 4.30it/s]\n 87%|████████▋ | 41/47 [00:09<00:01, 4.30it/s]\n 89%|████████▉ | 42/47 [00:09<00:01, 4.30it/s]\n 91%|█████████▏| 43/47 [00:09<00:00, 4.30it/s]\n 94%|█████████▎| 44/47 [00:10<00:00, 4.29it/s]\n 96%|█████████▌| 45/47 [00:10<00:00, 4.29it/s]\n 98%|█████████▊| 46/47 [00:10<00:00, 4.29it/s]\n100%|██████████| 47/47 [00:10<00:00, 4.29it/s]\n100%|██████████| 47/47 [00:10<00:00, 4.31it/s]\n 0%| | 0/3 [00:00<?, ?it/s]\n 33%|███▎ | 1/3 [00:00<00:00, 5.57it/s]\n 67%|██████▋ | 2/3 [00:00<00:00, 5.53it/s]\n100%|██████████| 3/3 [00:00<00:00, 5.52it/s]\n100%|██████████| 3/3 [00:00<00:00, 5.52it/s]", "metrics": { "predict_time": 12.636002, "total_time": 12.610641 }, "output": [ "https://pbxt.replicate.delivery/Jqr02n4TCP6tLdHm24XHM69BJD3h5TEdI2dUtZqwVoo1bAYE/out-0.png" ], "started_at": "2023-09-01T22:46:34.447039Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/elp5ytdbwzazyan4icerwlr43e", "cancel": "https://api.replicate.com/v1/predictions/elp5ytdbwzazyan4icerwlr43e/cancel" }, "version": "ed76ae3450e7d1c5b7b96f25a2899ed809defa85d72b1efbc1c9098d113b214a" }
Generated inUsing seed: 29752 Prompt: In the style of <s0><s1>, a photo of a creepy cat txt2img mode 0%| | 0/47 [00:00<?, ?it/s] 2%|▏ | 1/47 [00:00<00:10, 4.33it/s] 4%|▍ | 2/47 [00:00<00:10, 4.33it/s] 6%|▋ | 3/47 [00:00<00:10, 4.33it/s] 9%|▊ | 4/47 [00:00<00:09, 4.33it/s] 11%|█ | 5/47 [00:01<00:09, 4.33it/s] 13%|█▎ | 6/47 [00:01<00:09, 4.33it/s] 15%|█▍ | 7/47 [00:01<00:09, 4.33it/s] 17%|█▋ | 8/47 [00:01<00:09, 4.33it/s] 19%|█▉ | 9/47 [00:02<00:08, 4.32it/s] 21%|██▏ | 10/47 [00:02<00:08, 4.32it/s] 23%|██▎ | 11/47 [00:02<00:08, 4.32it/s] 26%|██▌ | 12/47 [00:02<00:08, 4.32it/s] 28%|██▊ | 13/47 [00:03<00:07, 4.32it/s] 30%|██▉ | 14/47 [00:03<00:07, 4.32it/s] 32%|███▏ | 15/47 [00:03<00:07, 4.31it/s] 34%|███▍ | 16/47 [00:03<00:07, 4.31it/s] 36%|███▌ | 17/47 [00:03<00:06, 4.31it/s] 38%|███▊ | 18/47 [00:04<00:06, 4.31it/s] 40%|████ | 19/47 [00:04<00:06, 4.31it/s] 43%|████▎ | 20/47 [00:04<00:06, 4.31it/s] 45%|████▍ | 21/47 [00:04<00:06, 4.31it/s] 47%|████▋ | 22/47 [00:05<00:05, 4.31it/s] 49%|████▉ | 23/47 [00:05<00:05, 4.31it/s] 51%|█████ | 24/47 [00:05<00:05, 4.31it/s] 53%|█████▎ | 25/47 [00:05<00:05, 4.31it/s] 55%|█████▌ | 26/47 [00:06<00:04, 4.30it/s] 57%|█████▋ | 27/47 [00:06<00:04, 4.31it/s] 60%|█████▉ | 28/47 [00:06<00:04, 4.31it/s] 62%|██████▏ | 29/47 [00:06<00:04, 4.31it/s] 64%|██████▍ | 30/47 [00:06<00:03, 4.30it/s] 66%|██████▌ | 31/47 [00:07<00:03, 4.30it/s] 68%|██████▊ | 32/47 [00:07<00:03, 4.30it/s] 70%|███████ | 33/47 [00:07<00:03, 4.30it/s] 72%|███████▏ | 34/47 [00:07<00:03, 4.30it/s] 74%|███████▍ | 35/47 [00:08<00:02, 4.30it/s] 77%|███████▋ | 36/47 [00:08<00:02, 4.30it/s] 79%|███████▊ | 37/47 [00:08<00:02, 4.30it/s] 81%|████████ | 38/47 [00:08<00:02, 4.30it/s] 83%|████████▎ | 39/47 [00:09<00:01, 4.30it/s] 85%|████████▌ | 40/47 [00:09<00:01, 4.30it/s] 87%|████████▋ | 41/47 [00:09<00:01, 4.30it/s] 89%|████████▉ | 42/47 [00:09<00:01, 4.30it/s] 91%|█████████▏| 43/47 [00:09<00:00, 4.30it/s] 94%|█████████▎| 44/47 [00:10<00:00, 4.29it/s] 96%|█████████▌| 45/47 [00:10<00:00, 4.29it/s] 98%|█████████▊| 46/47 [00:10<00:00, 4.29it/s] 100%|██████████| 47/47 [00:10<00:00, 4.29it/s] 100%|██████████| 47/47 [00:10<00:00, 4.31it/s] 0%| | 0/3 [00:00<?, ?it/s] 33%|███▎ | 1/3 [00:00<00:00, 5.57it/s] 67%|██████▋ | 2/3 [00:00<00:00, 5.53it/s] 100%|██████████| 3/3 [00:00<00:00, 5.52it/s] 100%|██████████| 3/3 [00:00<00:00, 5.52it/s]
Want to make some of these yourself?
Run this model