adiba-shahana / sdxl-large-fine-tuned
(Updated 1 year, 3 months ago)
- Public
- 84 runs
- SDXL fine-tune
Prediction
adiba-shahana/sdxl-large-fine-tuned:49385a24fadb595a10ef6ec6425ef3f07781ba611ec33b0bad66cff8ae41abcbIDrk3pey3bdeaqcgx6ucfrfuk6eeStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 1234
- width
- 1024
- height
- 1024
- prompt
- In a style of tile, a mettalic finish modern marble design , elegant veins
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 4
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- different color, low resolution
- prompt_strength
- 0.3
- num_inference_steps
- 50
{ "seed": 1234, "image": "https://replicate.delivery/pbxt/KS5oPMxDwH3eMjiiw82aZzUNKoyHQMbtRaj86J7SP4l29Fhj/generated_89-C-GS-ATBEDKF30A-ATLAS%20BEIGE%20DK%20FL%20A%20300X300MM.jpg.380x380_q85.jpg", "width": 1024, "height": 1024, "prompt": "In a style of tile, a mettalic finish modern marble design , elegant veins", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "different color, low resolution", "prompt_strength": 0.3, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run adiba-shahana/sdxl-large-fine-tuned using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "adiba-shahana/sdxl-large-fine-tuned:49385a24fadb595a10ef6ec6425ef3f07781ba611ec33b0bad66cff8ae41abcb", { input: { seed: 1234, image: "https://replicate.delivery/pbxt/KS5oPMxDwH3eMjiiw82aZzUNKoyHQMbtRaj86J7SP4l29Fhj/generated_89-C-GS-ATBEDKF30A-ATLAS%20BEIGE%20DK%20FL%20A%20300X300MM.jpg.380x380_q85.jpg", width: 1024, height: 1024, prompt: "In a style of tile, a mettalic finish modern marble design , elegant veins", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 4, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "different color, low resolution", prompt_strength: 0.3, 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 replicate
Import the client:import replicate
Run adiba-shahana/sdxl-large-fine-tuned using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "adiba-shahana/sdxl-large-fine-tuned:49385a24fadb595a10ef6ec6425ef3f07781ba611ec33b0bad66cff8ae41abcb", input={ "seed": 1234, "image": "https://replicate.delivery/pbxt/KS5oPMxDwH3eMjiiw82aZzUNKoyHQMbtRaj86J7SP4l29Fhj/generated_89-C-GS-ATBEDKF30A-ATLAS%20BEIGE%20DK%20FL%20A%20300X300MM.jpg.380x380_q85.jpg", "width": 1024, "height": 1024, "prompt": "In a style of tile, a mettalic finish modern marble design , elegant veins", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "different color, low resolution", "prompt_strength": 0.3, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run adiba-shahana/sdxl-large-fine-tuned 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": "adiba-shahana/sdxl-large-fine-tuned:49385a24fadb595a10ef6ec6425ef3f07781ba611ec33b0bad66cff8ae41abcb", "input": { "seed": 1234, "image": "https://replicate.delivery/pbxt/KS5oPMxDwH3eMjiiw82aZzUNKoyHQMbtRaj86J7SP4l29Fhj/generated_89-C-GS-ATBEDKF30A-ATLAS%20BEIGE%20DK%20FL%20A%20300X300MM.jpg.380x380_q85.jpg", "width": 1024, "height": 1024, "prompt": "In a style of tile, a mettalic finish modern marble design , elegant veins", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "different color, low resolution", "prompt_strength": 0.3, "num_inference_steps": 50 } }' \ 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/adiba-shahana/sdxl-large-fine-tuned@sha256:49385a24fadb595a10ef6ec6425ef3f07781ba611ec33b0bad66cff8ae41abcb \ -i 'seed=1234' \ -i 'image="https://replicate.delivery/pbxt/KS5oPMxDwH3eMjiiw82aZzUNKoyHQMbtRaj86J7SP4l29Fhj/generated_89-C-GS-ATBEDKF30A-ATLAS%20BEIGE%20DK%20FL%20A%20300X300MM.jpg.380x380_q85.jpg"' \ -i 'width=1024' \ -i 'height=1024' \ -i 'prompt="In a style of tile, a mettalic finish modern marble design , elegant veins"' \ -i 'refine="no_refiner"' \ -i 'scheduler="K_EULER"' \ -i 'lora_scale=0.6' \ -i 'num_outputs=4' \ -i 'guidance_scale=7.5' \ -i 'apply_watermark=true' \ -i 'high_noise_frac=0.8' \ -i 'negative_prompt="different color, low resolution"' \ -i 'prompt_strength=0.3' \ -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/adiba-shahana/sdxl-large-fine-tuned@sha256:49385a24fadb595a10ef6ec6425ef3f07781ba611ec33b0bad66cff8ae41abcb
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 1234, "image": "https://replicate.delivery/pbxt/KS5oPMxDwH3eMjiiw82aZzUNKoyHQMbtRaj86J7SP4l29Fhj/generated_89-C-GS-ATBEDKF30A-ATLAS%20BEIGE%20DK%20FL%20A%20300X300MM.jpg.380x380_q85.jpg", "width": 1024, "height": 1024, "prompt": "In a style of tile, a mettalic finish modern marble design , elegant veins", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "different color, low resolution", "prompt_strength": 0.3, "num_inference_steps": 50 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{ "completed_at": "2024-02-23T05:43:31.513197Z", "created_at": "2024-02-23T05:43:15.521429Z", "data_removed": false, "error": null, "id": "rk3pey3bdeaqcgx6ucfrfuk6ee", "input": { "seed": 1234, "image": "https://replicate.delivery/pbxt/KS5oPMxDwH3eMjiiw82aZzUNKoyHQMbtRaj86J7SP4l29Fhj/generated_89-C-GS-ATBEDKF30A-ATLAS%20BEIGE%20DK%20FL%20A%20300X300MM.jpg.380x380_q85.jpg", "width": 1024, "height": 1024, "prompt": "In a style of tile, a mettalic finish modern marble design , elegant veins", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 4, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "different color, low resolution", "prompt_strength": 0.3, "num_inference_steps": 50 }, "logs": "Using seed: 1234\nEnsuring enough disk space...\nFree disk space: 1362282278912\nDownloading weights: https://replicate.delivery/pbxt/EyTpk37hR16ZHhNSoTbJ05W691fn0f3eHSnlZbuvWDjBJRykA/trained_model.tar\n2024-02-23T05:43:19Z | INFO | [ Initiating ] dest=/src/weights-cache/800713987ecee3b0 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/EyTpk37hR16ZHhNSoTbJ05W691fn0f3eHSnlZbuvWDjBJRykA/trained_model.tar\n2024-02-23T05:43:26Z | INFO | [ Complete ] dest=/src/weights-cache/800713987ecee3b0 size=\"186 MB\" total_elapsed=6.381s url=https://replicate.delivery/pbxt/EyTpk37hR16ZHhNSoTbJ05W691fn0f3eHSnlZbuvWDjBJRykA/trained_model.tar\nb''\nDownloaded weights in 6.5203540325164795 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: In a style of tile, a mettalic finish modern marble design , elegant veins\nimg2img mode\n 0%| | 0/15 [00:00<?, ?it/s]\n 7%|▋ | 1/15 [00:00<00:02, 4.89it/s]\n 13%|█▎ | 2/15 [00:00<00:02, 5.60it/s]\n 20%|██ | 3/15 [00:00<00:02, 5.84it/s]\n 27%|██▋ | 4/15 [00:00<00:01, 5.96it/s]\n 33%|███▎ | 5/15 [00:00<00:01, 6.03it/s]\n 40%|████ | 6/15 [00:01<00:01, 6.08it/s]\n 47%|████▋ | 7/15 [00:01<00:01, 6.10it/s]\n 53%|█████▎ | 8/15 [00:01<00:01, 6.14it/s]\n 60%|██████ | 9/15 [00:01<00:00, 6.16it/s]\n 67%|██████▋ | 10/15 [00:01<00:00, 6.17it/s]\n 73%|███████▎ | 11/15 [00:01<00:00, 6.18it/s]\n 80%|████████ | 12/15 [00:01<00:00, 6.18it/s]\n 87%|████████▋ | 13/15 [00:02<00:00, 6.19it/s]\n 93%|█████████▎| 14/15 [00:02<00:00, 6.19it/s]\n100%|██████████| 15/15 [00:02<00:00, 6.19it/s]\n100%|██████████| 15/15 [00:02<00:00, 6.08it/s]\nPotential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed.\nNSFW content detected in image 0", "metrics": { "predict_time": 12.230371, "total_time": 15.991768 }, "output": [ "https://replicate.delivery/pbxt/YV3LPaSebw2gBCQVhmOlN9BQoL1CBWLeGbeT4WfweUQNQxLTC/out-1.png", "https://replicate.delivery/pbxt/X9VfSPa9ZBxkd6emHVBylfjOalbwtYQ1juJnGJ5flFqJo4lJB/out-2.png", "https://replicate.delivery/pbxt/aZtQE7UzUU6GN1VZdA2fYX3MaTeYnMznwmS6GCh7Ld2DKeykA/out-3.png" ], "started_at": "2024-02-23T05:43:19.282826Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/rk3pey3bdeaqcgx6ucfrfuk6ee", "cancel": "https://api.replicate.com/v1/predictions/rk3pey3bdeaqcgx6ucfrfuk6ee/cancel" }, "version": "49385a24fadb595a10ef6ec6425ef3f07781ba611ec33b0bad66cff8ae41abcb" }
Generated inUsing seed: 1234 Ensuring enough disk space... Free disk space: 1362282278912 Downloading weights: https://replicate.delivery/pbxt/EyTpk37hR16ZHhNSoTbJ05W691fn0f3eHSnlZbuvWDjBJRykA/trained_model.tar 2024-02-23T05:43:19Z | INFO | [ Initiating ] dest=/src/weights-cache/800713987ecee3b0 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/EyTpk37hR16ZHhNSoTbJ05W691fn0f3eHSnlZbuvWDjBJRykA/trained_model.tar 2024-02-23T05:43:26Z | INFO | [ Complete ] dest=/src/weights-cache/800713987ecee3b0 size="186 MB" total_elapsed=6.381s url=https://replicate.delivery/pbxt/EyTpk37hR16ZHhNSoTbJ05W691fn0f3eHSnlZbuvWDjBJRykA/trained_model.tar b'' Downloaded weights in 6.5203540325164795 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: In a style of tile, a mettalic finish modern marble design , elegant veins img2img mode 0%| | 0/15 [00:00<?, ?it/s] 7%|▋ | 1/15 [00:00<00:02, 4.89it/s] 13%|█▎ | 2/15 [00:00<00:02, 5.60it/s] 20%|██ | 3/15 [00:00<00:02, 5.84it/s] 27%|██▋ | 4/15 [00:00<00:01, 5.96it/s] 33%|███▎ | 5/15 [00:00<00:01, 6.03it/s] 40%|████ | 6/15 [00:01<00:01, 6.08it/s] 47%|████▋ | 7/15 [00:01<00:01, 6.10it/s] 53%|█████▎ | 8/15 [00:01<00:01, 6.14it/s] 60%|██████ | 9/15 [00:01<00:00, 6.16it/s] 67%|██████▋ | 10/15 [00:01<00:00, 6.17it/s] 73%|███████▎ | 11/15 [00:01<00:00, 6.18it/s] 80%|████████ | 12/15 [00:01<00:00, 6.18it/s] 87%|████████▋ | 13/15 [00:02<00:00, 6.19it/s] 93%|█████████▎| 14/15 [00:02<00:00, 6.19it/s] 100%|██████████| 15/15 [00:02<00:00, 6.19it/s] 100%|██████████| 15/15 [00:02<00:00, 6.08it/s] Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed. NSFW content detected in image 0
Want to make some of these yourself?
Run this model