cbh123 / sdxl-shining
SDXL fine-tuned on The Shining
- Public
- 4.8K runs
-
L40S
- SDXL fine-tune
Prediction
cbh123/sdxl-shining:0d57287eb01a0684fdc3dff4d6dbd2e84d61d6c4cf9f206583a6f43fd467fdceIDnz46dklb7ylmkwhvhbs6vzjnb4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- mask
- null
- seed
- null
- image
- null
- width
- 1024
- height
- 1024
- prompt
- a photo of a hallway in the style of TOK
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- refine_steps
- null
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "mask": null, "seed": null, "image": null, "width": 1024, "height": 1024, "prompt": "a photo of a hallway in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "refine_steps": null, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }Install Replicate’s Node.js client library:npm install replicateImport and set up the client:import Replicate from "replicate"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });Run cbh123/sdxl-shining using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "cbh123/sdxl-shining:0d57287eb01a0684fdc3dff4d6dbd2e84d61d6c4cf9f206583a6f43fd467fdce", { input: { width: 1024, height: 1024, prompt: "a photo of a hallway in the style of TOK", 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: "", prompt_strength: 0.8, num_inference_steps: 50 } } ); // 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 replicateImport the client:import replicateRun cbh123/sdxl-shining using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "cbh123/sdxl-shining:0d57287eb01a0684fdc3dff4d6dbd2e84d61d6c4cf9f206583a6f43fd467fdce", input={ "width": 1024, "height": 1024, "prompt": "a photo of a hallway in the style of TOK", "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": "", "prompt_strength": 0.8, "num_inference_steps": 50 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run cbh123/sdxl-shining 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": "cbh123/sdxl-shining:0d57287eb01a0684fdc3dff4d6dbd2e84d61d6c4cf9f206583a6f43fd467fdce", "input": { "width": 1024, "height": 1024, "prompt": "a photo of a hallway in the style of TOK", "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": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
You can run this model locally using Cog. First, install Cog:brew install cogIf you don’t have Homebrew, there are other installation options available.
Run this to download the model and run it in your local environment:
cog predict r8.im/cbh123/sdxl-shining@sha256:0d57287eb01a0684fdc3dff4d6dbd2e84d61d6c4cf9f206583a6f43fd467fdce \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="a photo of a hallway in the style of TOK"' \ -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=""' \ -i 'prompt_strength=0.8' \ -i 'num_inference_steps=50'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/cbh123/sdxl-shining@sha256:0d57287eb01a0684fdc3dff4d6dbd2e84d61d6c4cf9f206583a6f43fd467fdcecurl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "a photo of a hallway in the style of TOK", "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": "", "prompt_strength": 0.8, "num_inference_steps": 50 } }' \ http://localhost:5000/predictionsTo learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2023-10-30T18:20:35.319435Z", "created_at": "2023-10-30T18:20:09.847672Z", "data_removed": false, "error": null, "id": "nz46dklb7ylmkwhvhbs6vzjnb4", "input": { "mask": null, "seed": null, "image": null, "width": 1024, "height": 1024, "prompt": "a photo of a hallway in the style of TOK", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "refine_steps": null, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 63496\nEnsuring enough disk space...\nFree disk space: 1852196315136\nDownloading weights: https://pbxt.replicate.delivery/d9v1n5fzWKUBOqeCiAAN97xI3X69WxYWp6HDvy5nogFFJZzRA/trained_model.tar\nb'Downloaded 186 MB bytes in 4.985s (37 MB/s)\\nExtracted 186 MB in 0.074s (2.5 GB/s)\\n'\nDownloaded weights in 5.74027943611145 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a photo of a hallway in the style of <s0><s1>\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:14, 3.47it/s]\n 4%|▍ | 2/50 [00:00<00:13, 3.47it/s]\n 6%|▌ | 3/50 [00:00<00:13, 3.46it/s]\n 8%|▊ | 4/50 [00:01<00:13, 3.46it/s]\n 10%|█ | 5/50 [00:01<00:13, 3.45it/s]\n 12%|█▏ | 6/50 [00:01<00:12, 3.45it/s]\n 14%|█▍ | 7/50 [00:02<00:12, 3.45it/s]\n 16%|█▌ | 8/50 [00:02<00:12, 3.45it/s]\n 18%|█▊ | 9/50 [00:02<00:11, 3.45it/s]\n 20%|██ | 10/50 [00:02<00:11, 3.45it/s]\n 22%|██▏ | 11/50 [00:03<00:11, 3.44it/s]\n 24%|██▍ | 12/50 [00:03<00:11, 3.44it/s]\n 26%|██▌ | 13/50 [00:03<00:10, 3.44it/s]\n 28%|██▊ | 14/50 [00:04<00:10, 3.44it/s]\n 30%|███ | 15/50 [00:04<00:10, 3.44it/s]\n 32%|███▏ | 16/50 [00:04<00:09, 3.44it/s]\n 34%|███▍ | 17/50 [00:04<00:09, 3.44it/s]\n 36%|███▌ | 18/50 [00:05<00:09, 3.44it/s]\n 38%|███▊ | 19/50 [00:05<00:09, 3.43it/s]\n 40%|████ | 20/50 [00:05<00:08, 3.43it/s]\n 42%|████▏ | 21/50 [00:06<00:08, 3.44it/s]\n 44%|████▍ | 22/50 [00:06<00:08, 3.44it/s]\n 46%|████▌ | 23/50 [00:06<00:07, 3.44it/s]\n 48%|████▊ | 24/50 [00:06<00:07, 3.43it/s]\n 50%|█████ | 25/50 [00:07<00:07, 3.43it/s]\n 52%|█████▏ | 26/50 [00:07<00:06, 3.43it/s]\n 54%|█████▍ | 27/50 [00:07<00:06, 3.43it/s]\n 56%|█████▌ | 28/50 [00:08<00:06, 3.43it/s]\n 58%|█████▊ | 29/50 [00:08<00:06, 3.43it/s]\n 60%|██████ | 30/50 [00:08<00:05, 3.43it/s]\n 62%|██████▏ | 31/50 [00:09<00:05, 3.43it/s]\n 64%|██████▍ | 32/50 [00:09<00:05, 3.43it/s]\n 66%|██████▌ | 33/50 [00:09<00:04, 3.43it/s]\n 68%|██████▊ | 34/50 [00:09<00:04, 3.43it/s]\n 70%|███████ | 35/50 [00:10<00:04, 3.43it/s]\n 72%|███████▏ | 36/50 [00:10<00:04, 3.43it/s]\n 74%|███████▍ | 37/50 [00:10<00:03, 3.43it/s]\n 76%|███████▌ | 38/50 [00:11<00:03, 3.43it/s]\n 78%|███████▊ | 39/50 [00:11<00:03, 3.43it/s]\n 80%|████████ | 40/50 [00:11<00:02, 3.43it/s]\n 82%|████████▏ | 41/50 [00:11<00:02, 3.43it/s]\n 84%|████████▍ | 42/50 [00:12<00:02, 3.43it/s]\n 86%|████████▌ | 43/50 [00:12<00:02, 3.43it/s]\n 88%|████████▊ | 44/50 [00:12<00:01, 3.43it/s]\n 90%|█████████ | 45/50 [00:13<00:01, 3.43it/s]\n 92%|█████████▏| 46/50 [00:13<00:01, 3.43it/s]\n 94%|█████████▍| 47/50 [00:13<00:00, 3.43it/s]\n 96%|█████████▌| 48/50 [00:13<00:00, 3.43it/s]\n 98%|█████████▊| 49/50 [00:14<00:00, 3.43it/s]\n100%|██████████| 50/50 [00:14<00:00, 3.43it/s]\n100%|██████████| 50/50 [00:14<00:00, 3.44it/s]", "metrics": { "predict_time": 23.360273, "total_time": 25.471763 }, "output": [ "https://replicate.delivery/pbxt/Z9MRy99e841PHC8KR1Y4Iu6nycu9OcbDM3fDxeW4aHOkv0mjA/out-0.png" ], "started_at": "2023-10-30T18:20:11.959162Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/nz46dklb7ylmkwhvhbs6vzjnb4", "cancel": "https://api.replicate.com/v1/predictions/nz46dklb7ylmkwhvhbs6vzjnb4/cancel" }, "version": "0d57287eb01a0684fdc3dff4d6dbd2e84d61d6c4cf9f206583a6f43fd467fdce" }Generated inUsing seed: 63496 Ensuring enough disk space... Free disk space: 1852196315136 Downloading weights: https://pbxt.replicate.delivery/d9v1n5fzWKUBOqeCiAAN97xI3X69WxYWp6HDvy5nogFFJZzRA/trained_model.tar b'Downloaded 186 MB bytes in 4.985s (37 MB/s)\nExtracted 186 MB in 0.074s (2.5 GB/s)\n' Downloaded weights in 5.74027943611145 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a photo of a hallway in the style of <s0><s1> txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:14, 3.47it/s] 4%|▍ | 2/50 [00:00<00:13, 3.47it/s] 6%|▌ | 3/50 [00:00<00:13, 3.46it/s] 8%|▊ | 4/50 [00:01<00:13, 3.46it/s] 10%|█ | 5/50 [00:01<00:13, 3.45it/s] 12%|█▏ | 6/50 [00:01<00:12, 3.45it/s] 14%|█▍ | 7/50 [00:02<00:12, 3.45it/s] 16%|█▌ | 8/50 [00:02<00:12, 3.45it/s] 18%|█▊ | 9/50 [00:02<00:11, 3.45it/s] 20%|██ | 10/50 [00:02<00:11, 3.45it/s] 22%|██▏ | 11/50 [00:03<00:11, 3.44it/s] 24%|██▍ | 12/50 [00:03<00:11, 3.44it/s] 26%|██▌ | 13/50 [00:03<00:10, 3.44it/s] 28%|██▊ | 14/50 [00:04<00:10, 3.44it/s] 30%|███ | 15/50 [00:04<00:10, 3.44it/s] 32%|███▏ | 16/50 [00:04<00:09, 3.44it/s] 34%|███▍ | 17/50 [00:04<00:09, 3.44it/s] 36%|███▌ | 18/50 [00:05<00:09, 3.44it/s] 38%|███▊ | 19/50 [00:05<00:09, 3.43it/s] 40%|████ | 20/50 [00:05<00:08, 3.43it/s] 42%|████▏ | 21/50 [00:06<00:08, 3.44it/s] 44%|████▍ | 22/50 [00:06<00:08, 3.44it/s] 46%|████▌ | 23/50 [00:06<00:07, 3.44it/s] 48%|████▊ | 24/50 [00:06<00:07, 3.43it/s] 50%|█████ | 25/50 [00:07<00:07, 3.43it/s] 52%|█████▏ | 26/50 [00:07<00:06, 3.43it/s] 54%|█████▍ | 27/50 [00:07<00:06, 3.43it/s] 56%|█████▌ | 28/50 [00:08<00:06, 3.43it/s] 58%|█████▊ | 29/50 [00:08<00:06, 3.43it/s] 60%|██████ | 30/50 [00:08<00:05, 3.43it/s] 62%|██████▏ | 31/50 [00:09<00:05, 3.43it/s] 64%|██████▍ | 32/50 [00:09<00:05, 3.43it/s] 66%|██████▌ | 33/50 [00:09<00:04, 3.43it/s] 68%|██████▊ | 34/50 [00:09<00:04, 3.43it/s] 70%|███████ | 35/50 [00:10<00:04, 3.43it/s] 72%|███████▏ | 36/50 [00:10<00:04, 3.43it/s] 74%|███████▍ | 37/50 [00:10<00:03, 3.43it/s] 76%|███████▌ | 38/50 [00:11<00:03, 3.43it/s] 78%|███████▊ | 39/50 [00:11<00:03, 3.43it/s] 80%|████████ | 40/50 [00:11<00:02, 3.43it/s] 82%|████████▏ | 41/50 [00:11<00:02, 3.43it/s] 84%|████████▍ | 42/50 [00:12<00:02, 3.43it/s] 86%|████████▌ | 43/50 [00:12<00:02, 3.43it/s] 88%|████████▊ | 44/50 [00:12<00:01, 3.43it/s] 90%|█████████ | 45/50 [00:13<00:01, 3.43it/s] 92%|█████████▏| 46/50 [00:13<00:01, 3.43it/s] 94%|█████████▍| 47/50 [00:13<00:00, 3.43it/s] 96%|█████████▌| 48/50 [00:13<00:00, 3.43it/s] 98%|█████████▊| 49/50 [00:14<00:00, 3.43it/s] 100%|██████████| 50/50 [00:14<00:00, 3.43it/s] 100%|██████████| 50/50 [00:14<00:00, 3.44it/s]
Want to make some of these yourself?
Run this model
