adiba-shahana / fine-tune-iteration3
(Updated 1 year, 3 months ago)
- Public
- 454 runs
- SDXL fine-tune
Prediction
adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79IDurtq7utbl7waxk3ejm32w4f2jeStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a tile in design, dark brown, glossy
- refine
- base_image_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 2
- refine_steps
- 6
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- low resolution, not realistic
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a tile in design, dark brown, glossy", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 2, "refine_steps": 6, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "low resolution, not realistic", "prompt_strength": 0.8, "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/fine-tune-iteration3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", { input: { width: 1024, height: 1024, prompt: "a tile in design, dark brown, glossy", refine: "base_image_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 2, refine_steps: 6, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "low resolution, not realistic", 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 replicate
Import the client:import replicate
Run adiba-shahana/fine-tune-iteration3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", input={ "width": 1024, "height": 1024, "prompt": "a tile in design, dark brown, glossy", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 2, "refine_steps": 6, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "low resolution, not realistic", "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 adiba-shahana/fine-tune-iteration3 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/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", "input": { "width": 1024, "height": 1024, "prompt": "a tile in design, dark brown, glossy", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 2, "refine_steps": 6, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "low resolution, not realistic", "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.
Output
{ "completed_at": "2024-03-08T12:02:13.914780Z", "created_at": "2024-03-08T12:01:41.246053Z", "data_removed": false, "error": null, "id": "urtq7utbl7waxk3ejm32w4f2je", "input": { "width": 1024, "height": 1024, "prompt": "a tile in design, dark brown, glossy", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 2, "refine_steps": 6, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "low resolution, not realistic", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 60982\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a tile in design, dark brown, glossy\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:25, 1.89it/s]\n 4%|▍ | 2/50 [00:01<00:25, 1.88it/s]\n 6%|▌ | 3/50 [00:01<00:24, 1.88it/s]\n 8%|▊ | 4/50 [00:02<00:24, 1.88it/s]\n 10%|█ | 5/50 [00:02<00:23, 1.88it/s]\n 12%|█▏ | 6/50 [00:03<00:23, 1.89it/s]\n 14%|█▍ | 7/50 [00:03<00:22, 1.89it/s]\n 16%|█▌ | 8/50 [00:04<00:22, 1.89it/s]\n 18%|█▊ | 9/50 [00:04<00:21, 1.89it/s]\n 20%|██ | 10/50 [00:05<00:21, 1.89it/s]\n 22%|██▏ | 11/50 [00:05<00:20, 1.89it/s]\n 24%|██▍ | 12/50 [00:06<00:20, 1.89it/s]\n 26%|██▌ | 13/50 [00:06<00:19, 1.89it/s]\n 28%|██▊ | 14/50 [00:07<00:19, 1.88it/s]\n 30%|███ | 15/50 [00:07<00:18, 1.88it/s]\n 32%|███▏ | 16/50 [00:08<00:18, 1.88it/s]\n 34%|███▍ | 17/50 [00:09<00:17, 1.88it/s]\n 36%|███▌ | 18/50 [00:09<00:16, 1.89it/s]\n 38%|███▊ | 19/50 [00:10<00:16, 1.88it/s]\n 40%|████ | 20/50 [00:10<00:15, 1.88it/s]\n 42%|████▏ | 21/50 [00:11<00:15, 1.87it/s]\n 44%|████▍ | 22/50 [00:11<00:14, 1.88it/s]\n 46%|████▌ | 23/50 [00:12<00:14, 1.88it/s]\n 48%|████▊ | 24/50 [00:12<00:13, 1.88it/s]\n 50%|█████ | 25/50 [00:13<00:13, 1.88it/s]\n 52%|█████▏ | 26/50 [00:13<00:12, 1.88it/s]\n 54%|█████▍ | 27/50 [00:14<00:12, 1.88it/s]\n 56%|█████▌ | 28/50 [00:14<00:11, 1.88it/s]\n 58%|█████▊ | 29/50 [00:15<00:11, 1.88it/s]\n 60%|██████ | 30/50 [00:15<00:10, 1.88it/s]\n 62%|██████▏ | 31/50 [00:16<00:10, 1.89it/s]\n 64%|██████▍ | 32/50 [00:16<00:09, 1.89it/s]\n 66%|██████▌ | 33/50 [00:17<00:09, 1.88it/s]\n 68%|██████▊ | 34/50 [00:18<00:08, 1.88it/s]\n 70%|███████ | 35/50 [00:18<00:07, 1.88it/s]\n 72%|███████▏ | 36/50 [00:19<00:07, 1.88it/s]\n 74%|███████▍ | 37/50 [00:19<00:06, 1.88it/s]\n 76%|███████▌ | 38/50 [00:20<00:06, 1.88it/s]\n 78%|███████▊ | 39/50 [00:20<00:05, 1.88it/s]\n 80%|████████ | 40/50 [00:21<00:05, 1.88it/s]\n 82%|████████▏ | 41/50 [00:21<00:04, 1.88it/s]\n 84%|████████▍ | 42/50 [00:22<00:04, 1.88it/s]\n 86%|████████▌ | 43/50 [00:22<00:03, 1.88it/s]\n 88%|████████▊ | 44/50 [00:23<00:03, 1.88it/s]\n 90%|█████████ | 45/50 [00:23<00:02, 1.88it/s]\n 92%|█████████▏| 46/50 [00:24<00:02, 1.88it/s]\n 94%|█████████▍| 47/50 [00:24<00:01, 1.88it/s]\n 96%|█████████▌| 48/50 [00:25<00:01, 1.88it/s]\n 98%|█████████▊| 49/50 [00:26<00:00, 1.88it/s]\n100%|██████████| 50/50 [00:26<00:00, 1.88it/s]\n100%|██████████| 50/50 [00:26<00:00, 1.88it/s]\n 0%| | 0/1 [00:00<?, ?it/s]\n100%|██████████| 1/1 [00:00<00:00, 2.23it/s]\n100%|██████████| 1/1 [00:00<00:00, 2.23it/s]", "metrics": { "predict_time": 30.348083, "total_time": 32.668727 }, "output": [ "https://replicate.delivery/pbxt/6DYfmWAROnVnfkGmtu9AetZM3nzjKtyYeTRu1WfASJOuIYxTC/out-0.png", "https://replicate.delivery/pbxt/054CfT433zSoUa9VlwTfBLwErz24Prz7vYfwnm94VHIKCW8kA/out-1.png" ], "started_at": "2024-03-08T12:01:43.566697Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/urtq7utbl7waxk3ejm32w4f2je", "cancel": "https://api.replicate.com/v1/predictions/urtq7utbl7waxk3ejm32w4f2je/cancel" }, "version": "7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79" }
Generated inUsing seed: 60982 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a tile in design, dark brown, glossy txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:25, 1.89it/s] 4%|▍ | 2/50 [00:01<00:25, 1.88it/s] 6%|▌ | 3/50 [00:01<00:24, 1.88it/s] 8%|▊ | 4/50 [00:02<00:24, 1.88it/s] 10%|█ | 5/50 [00:02<00:23, 1.88it/s] 12%|█▏ | 6/50 [00:03<00:23, 1.89it/s] 14%|█▍ | 7/50 [00:03<00:22, 1.89it/s] 16%|█▌ | 8/50 [00:04<00:22, 1.89it/s] 18%|█▊ | 9/50 [00:04<00:21, 1.89it/s] 20%|██ | 10/50 [00:05<00:21, 1.89it/s] 22%|██▏ | 11/50 [00:05<00:20, 1.89it/s] 24%|██▍ | 12/50 [00:06<00:20, 1.89it/s] 26%|██▌ | 13/50 [00:06<00:19, 1.89it/s] 28%|██▊ | 14/50 [00:07<00:19, 1.88it/s] 30%|███ | 15/50 [00:07<00:18, 1.88it/s] 32%|███▏ | 16/50 [00:08<00:18, 1.88it/s] 34%|███▍ | 17/50 [00:09<00:17, 1.88it/s] 36%|███▌ | 18/50 [00:09<00:16, 1.89it/s] 38%|███▊ | 19/50 [00:10<00:16, 1.88it/s] 40%|████ | 20/50 [00:10<00:15, 1.88it/s] 42%|████▏ | 21/50 [00:11<00:15, 1.87it/s] 44%|████▍ | 22/50 [00:11<00:14, 1.88it/s] 46%|████▌ | 23/50 [00:12<00:14, 1.88it/s] 48%|████▊ | 24/50 [00:12<00:13, 1.88it/s] 50%|█████ | 25/50 [00:13<00:13, 1.88it/s] 52%|█████▏ | 26/50 [00:13<00:12, 1.88it/s] 54%|█████▍ | 27/50 [00:14<00:12, 1.88it/s] 56%|█████▌ | 28/50 [00:14<00:11, 1.88it/s] 58%|█████▊ | 29/50 [00:15<00:11, 1.88it/s] 60%|██████ | 30/50 [00:15<00:10, 1.88it/s] 62%|██████▏ | 31/50 [00:16<00:10, 1.89it/s] 64%|██████▍ | 32/50 [00:16<00:09, 1.89it/s] 66%|██████▌ | 33/50 [00:17<00:09, 1.88it/s] 68%|██████▊ | 34/50 [00:18<00:08, 1.88it/s] 70%|███████ | 35/50 [00:18<00:07, 1.88it/s] 72%|███████▏ | 36/50 [00:19<00:07, 1.88it/s] 74%|███████▍ | 37/50 [00:19<00:06, 1.88it/s] 76%|███████▌ | 38/50 [00:20<00:06, 1.88it/s] 78%|███████▊ | 39/50 [00:20<00:05, 1.88it/s] 80%|████████ | 40/50 [00:21<00:05, 1.88it/s] 82%|████████▏ | 41/50 [00:21<00:04, 1.88it/s] 84%|████████▍ | 42/50 [00:22<00:04, 1.88it/s] 86%|████████▌ | 43/50 [00:22<00:03, 1.88it/s] 88%|████████▊ | 44/50 [00:23<00:03, 1.88it/s] 90%|█████████ | 45/50 [00:23<00:02, 1.88it/s] 92%|█████████▏| 46/50 [00:24<00:02, 1.88it/s] 94%|█████████▍| 47/50 [00:24<00:01, 1.88it/s] 96%|█████████▌| 48/50 [00:25<00:01, 1.88it/s] 98%|█████████▊| 49/50 [00:26<00:00, 1.88it/s] 100%|██████████| 50/50 [00:26<00:00, 1.88it/s] 100%|██████████| 50/50 [00:26<00:00, 1.88it/s] 0%| | 0/1 [00:00<?, ?it/s] 100%|██████████| 1/1 [00:00<00:00, 2.23it/s] 100%|██████████| 1/1 [00:00<00:00, 2.23it/s]
Prediction
adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79ID5uqooetby5fb5fctfa5hvmu5ryStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- a tile in black , light structure, glossy , rectified
- 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
- low resolution, not realistic
- prompt_strength
- 0.2
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "a tile in black , light structure, glossy , rectified", "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": "low resolution, not realistic", "prompt_strength": 0.2, "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/fine-tune-iteration3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", { input: { width: 1024, height: 1024, prompt: "a tile in black , light structure, glossy , rectified", 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: "low resolution, not realistic", prompt_strength: 0.2, 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/fine-tune-iteration3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", input={ "width": 1024, "height": 1024, "prompt": "a tile in black , light structure, glossy , rectified", "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": "low resolution, not realistic", "prompt_strength": 0.2, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run adiba-shahana/fine-tune-iteration3 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/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", "input": { "width": 1024, "height": 1024, "prompt": "a tile in black , light structure, glossy , rectified", "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": "low resolution, not realistic", "prompt_strength": 0.2, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-03-08T11:15:01.369684Z", "created_at": "2024-03-08T11:14:35.083675Z", "data_removed": false, "error": null, "id": "5uqooetby5fb5fctfa5hvmu5ry", "input": { "width": 1024, "height": 1024, "prompt": "a tile in black , light structure, glossy , rectified", "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": "low resolution, not realistic", "prompt_strength": 0.2, "num_inference_steps": 50 }, "logs": "Using seed: 7223\nEnsuring enough disk space...\nFree disk space: 2108365447168\nDownloading weights: https://replicate.delivery/pbxt/gfHYMAPiORxDGKObDHfp9wZU5k1XlzueAKup9VSkPswBem4JB/trained_model.tar\n2024-03-08T11:14:43Z | INFO | [ Initiating ] dest=/src/weights-cache/c07794c511156684 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/gfHYMAPiORxDGKObDHfp9wZU5k1XlzueAKup9VSkPswBem4JB/trained_model.tar\n2024-03-08T11:14:44Z | INFO | [ Complete ] dest=/src/weights-cache/c07794c511156684 size=\"186 MB\" total_elapsed=0.686s url=https://replicate.delivery/pbxt/gfHYMAPiORxDGKObDHfp9wZU5k1XlzueAKup9VSkPswBem4JB/trained_model.tar\nb''\nDownloaded weights in 0.9484007358551025 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a tile in black , light structure, glossy , rectified\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:13, 3.67it/s]\n 4%|▍ | 2/50 [00:00<00:13, 3.64it/s]\n 6%|▌ | 3/50 [00:00<00:12, 3.64it/s]\n 8%|▊ | 4/50 [00:01<00:12, 3.62it/s]\n 10%|█ | 5/50 [00:01<00:12, 3.62it/s]\n 12%|█▏ | 6/50 [00:01<00:12, 3.62it/s]\n 14%|█▍ | 7/50 [00:01<00:11, 3.62it/s]\n 16%|█▌ | 8/50 [00:02<00:11, 3.62it/s]\n 18%|█▊ | 9/50 [00:02<00:11, 3.62it/s]\n 20%|██ | 10/50 [00:02<00:11, 3.62it/s]\n 22%|██▏ | 11/50 [00:03<00:10, 3.62it/s]\n 24%|██▍ | 12/50 [00:03<00:10, 3.62it/s]\n 26%|██▌ | 13/50 [00:03<00:10, 3.61it/s]\n 28%|██▊ | 14/50 [00:03<00:09, 3.61it/s]\n 30%|███ | 15/50 [00:04<00:09, 3.61it/s]\n 32%|███▏ | 16/50 [00:04<00:09, 3.61it/s]\n 34%|███▍ | 17/50 [00:04<00:09, 3.62it/s]\n 36%|███▌ | 18/50 [00:04<00:08, 3.61it/s]\n 38%|███▊ | 19/50 [00:05<00:08, 3.61it/s]\n 40%|████ | 20/50 [00:05<00:08, 3.61it/s]\n 42%|████▏ | 21/50 [00:05<00:08, 3.61it/s]\n 44%|████▍ | 22/50 [00:06<00:07, 3.61it/s]\n 46%|████▌ | 23/50 [00:06<00:07, 3.61it/s]\n 48%|████▊ | 24/50 [00:06<00:07, 3.61it/s]\n 50%|█████ | 25/50 [00:06<00:06, 3.61it/s]\n 52%|█████▏ | 26/50 [00:07<00:06, 3.60it/s]\n 54%|█████▍ | 27/50 [00:07<00:06, 3.61it/s]\n 56%|█████▌ | 28/50 [00:07<00:06, 3.60it/s]\n 58%|█████▊ | 29/50 [00:08<00:05, 3.60it/s]\n 60%|██████ | 30/50 [00:08<00:05, 3.60it/s]\n 62%|██████▏ | 31/50 [00:08<00:05, 3.60it/s]\n 64%|██████▍ | 32/50 [00:08<00:04, 3.60it/s]\n 66%|██████▌ | 33/50 [00:09<00:04, 3.60it/s]\n 68%|██████▊ | 34/50 [00:09<00:04, 3.61it/s]\n 70%|███████ | 35/50 [00:09<00:04, 3.61it/s]\n 72%|███████▏ | 36/50 [00:09<00:03, 3.60it/s]\n 74%|███████▍ | 37/50 [00:10<00:03, 3.61it/s]\n 76%|███████▌ | 38/50 [00:10<00:03, 3.60it/s]\n 78%|███████▊ | 39/50 [00:10<00:03, 3.61it/s]\n 80%|████████ | 40/50 [00:11<00:02, 3.61it/s]\n 82%|████████▏ | 41/50 [00:11<00:02, 3.58it/s]\n 84%|████████▍ | 42/50 [00:11<00:02, 3.59it/s]\n 86%|████████▌ | 43/50 [00:11<00:01, 3.59it/s]\n 88%|████████▊ | 44/50 [00:12<00:01, 3.60it/s]\n 90%|█████████ | 45/50 [00:12<00:01, 3.60it/s]\n 92%|█████████▏| 46/50 [00:12<00:01, 3.60it/s]\n 94%|█████████▍| 47/50 [00:13<00:00, 3.61it/s]\n 96%|█████████▌| 48/50 [00:13<00:00, 3.61it/s]\n 98%|█████████▊| 49/50 [00:13<00:00, 3.60it/s]\n100%|██████████| 50/50 [00:13<00:00, 3.60it/s]\n100%|██████████| 50/50 [00:13<00:00, 3.61it/s]", "metrics": { "predict_time": 18.01453, "total_time": 26.286009 }, "output": [ "https://replicate.delivery/pbxt/92n7fsNgyR32YSb2ym88OHkVQIE9AdFAGlf5r8nTmY1zUKekA/out-0.png" ], "started_at": "2024-03-08T11:14:43.355154Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/5uqooetby5fb5fctfa5hvmu5ry", "cancel": "https://api.replicate.com/v1/predictions/5uqooetby5fb5fctfa5hvmu5ry/cancel" }, "version": "7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79" }
Generated inUsing seed: 7223 Ensuring enough disk space... Free disk space: 2108365447168 Downloading weights: https://replicate.delivery/pbxt/gfHYMAPiORxDGKObDHfp9wZU5k1XlzueAKup9VSkPswBem4JB/trained_model.tar 2024-03-08T11:14:43Z | INFO | [ Initiating ] dest=/src/weights-cache/c07794c511156684 minimum_chunk_size=150M url=https://replicate.delivery/pbxt/gfHYMAPiORxDGKObDHfp9wZU5k1XlzueAKup9VSkPswBem4JB/trained_model.tar 2024-03-08T11:14:44Z | INFO | [ Complete ] dest=/src/weights-cache/c07794c511156684 size="186 MB" total_elapsed=0.686s url=https://replicate.delivery/pbxt/gfHYMAPiORxDGKObDHfp9wZU5k1XlzueAKup9VSkPswBem4JB/trained_model.tar b'' Downloaded weights in 0.9484007358551025 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a tile in black , light structure, glossy , rectified txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:13, 3.67it/s] 4%|▍ | 2/50 [00:00<00:13, 3.64it/s] 6%|▌ | 3/50 [00:00<00:12, 3.64it/s] 8%|▊ | 4/50 [00:01<00:12, 3.62it/s] 10%|█ | 5/50 [00:01<00:12, 3.62it/s] 12%|█▏ | 6/50 [00:01<00:12, 3.62it/s] 14%|█▍ | 7/50 [00:01<00:11, 3.62it/s] 16%|█▌ | 8/50 [00:02<00:11, 3.62it/s] 18%|█▊ | 9/50 [00:02<00:11, 3.62it/s] 20%|██ | 10/50 [00:02<00:11, 3.62it/s] 22%|██▏ | 11/50 [00:03<00:10, 3.62it/s] 24%|██▍ | 12/50 [00:03<00:10, 3.62it/s] 26%|██▌ | 13/50 [00:03<00:10, 3.61it/s] 28%|██▊ | 14/50 [00:03<00:09, 3.61it/s] 30%|███ | 15/50 [00:04<00:09, 3.61it/s] 32%|███▏ | 16/50 [00:04<00:09, 3.61it/s] 34%|███▍ | 17/50 [00:04<00:09, 3.62it/s] 36%|███▌ | 18/50 [00:04<00:08, 3.61it/s] 38%|███▊ | 19/50 [00:05<00:08, 3.61it/s] 40%|████ | 20/50 [00:05<00:08, 3.61it/s] 42%|████▏ | 21/50 [00:05<00:08, 3.61it/s] 44%|████▍ | 22/50 [00:06<00:07, 3.61it/s] 46%|████▌ | 23/50 [00:06<00:07, 3.61it/s] 48%|████▊ | 24/50 [00:06<00:07, 3.61it/s] 50%|█████ | 25/50 [00:06<00:06, 3.61it/s] 52%|█████▏ | 26/50 [00:07<00:06, 3.60it/s] 54%|█████▍ | 27/50 [00:07<00:06, 3.61it/s] 56%|█████▌ | 28/50 [00:07<00:06, 3.60it/s] 58%|█████▊ | 29/50 [00:08<00:05, 3.60it/s] 60%|██████ | 30/50 [00:08<00:05, 3.60it/s] 62%|██████▏ | 31/50 [00:08<00:05, 3.60it/s] 64%|██████▍ | 32/50 [00:08<00:04, 3.60it/s] 66%|██████▌ | 33/50 [00:09<00:04, 3.60it/s] 68%|██████▊ | 34/50 [00:09<00:04, 3.61it/s] 70%|███████ | 35/50 [00:09<00:04, 3.61it/s] 72%|███████▏ | 36/50 [00:09<00:03, 3.60it/s] 74%|███████▍ | 37/50 [00:10<00:03, 3.61it/s] 76%|███████▌ | 38/50 [00:10<00:03, 3.60it/s] 78%|███████▊ | 39/50 [00:10<00:03, 3.61it/s] 80%|████████ | 40/50 [00:11<00:02, 3.61it/s] 82%|████████▏ | 41/50 [00:11<00:02, 3.58it/s] 84%|████████▍ | 42/50 [00:11<00:02, 3.59it/s] 86%|████████▌ | 43/50 [00:11<00:01, 3.59it/s] 88%|████████▊ | 44/50 [00:12<00:01, 3.60it/s] 90%|█████████ | 45/50 [00:12<00:01, 3.60it/s] 92%|█████████▏| 46/50 [00:12<00:01, 3.60it/s] 94%|█████████▍| 47/50 [00:13<00:00, 3.61it/s] 96%|█████████▌| 48/50 [00:13<00:00, 3.61it/s] 98%|█████████▊| 49/50 [00:13<00:00, 3.60it/s] 100%|██████████| 50/50 [00:13<00:00, 3.60it/s] 100%|██████████| 50/50 [00:13<00:00, 3.61it/s]
Prediction
adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79IDpv6e4wtbf4xp6ec7chpdav3xveStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 6000
- width
- 1024
- height
- 1024
- prompt
- a marble design tile, dark brown, glossy
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 2
- refine_steps
- 10
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.4
- negative_prompt
- low resolution, not realistic
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "seed": 6000, "image": "https://replicate.delivery/pbxt/KX9kYl34cIzES5vChSISzIK3y5vBShm9likMRM9VLsVQcoyz/tile%20%284%29.jpg", "width": 1024, "height": 1024, "prompt": "a marble design tile, dark brown, glossy", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 2, "refine_steps": 10, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.4, "negative_prompt": "low resolution, not realistic", "prompt_strength": 0.8, "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/fine-tune-iteration3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", { input: { seed: 6000, image: "https://replicate.delivery/pbxt/KX9kYl34cIzES5vChSISzIK3y5vBShm9likMRM9VLsVQcoyz/tile%20%284%29.jpg", width: 1024, height: 1024, prompt: "a marble design tile, dark brown, glossy", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 2, refine_steps: 10, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.4, negative_prompt: "low resolution, not realistic", 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 replicate
Import the client:import replicate
Run adiba-shahana/fine-tune-iteration3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "adiba-shahana/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", input={ "seed": 6000, "image": "https://replicate.delivery/pbxt/KX9kYl34cIzES5vChSISzIK3y5vBShm9likMRM9VLsVQcoyz/tile%20%284%29.jpg", "width": 1024, "height": 1024, "prompt": "a marble design tile, dark brown, glossy", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 2, "refine_steps": 10, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.4, "negative_prompt": "low resolution, not realistic", "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 adiba-shahana/fine-tune-iteration3 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/fine-tune-iteration3:7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79", "input": { "seed": 6000, "image": "https://replicate.delivery/pbxt/KX9kYl34cIzES5vChSISzIK3y5vBShm9likMRM9VLsVQcoyz/tile%20%284%29.jpg", "width": 1024, "height": 1024, "prompt": "a marble design tile, dark brown, glossy", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 2, "refine_steps": 10, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.4, "negative_prompt": "low resolution, not realistic", "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.
Output
{ "completed_at": "2024-03-08T12:05:17.669613Z", "created_at": "2024-03-08T12:05:07.925792Z", "data_removed": false, "error": null, "id": "pv6e4wtbf4xp6ec7chpdav3xve", "input": { "seed": 6000, "image": "https://replicate.delivery/pbxt/KX9kYl34cIzES5vChSISzIK3y5vBShm9likMRM9VLsVQcoyz/tile%20%284%29.jpg", "width": 1024, "height": 1024, "prompt": "a marble design tile, dark brown, glossy", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 2, "refine_steps": 10, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.4, "negative_prompt": "low resolution, not realistic", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 6000\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a marble design tile, dark brown, glossy\nimg2img mode\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:01, 5.22it/s]\n 20%|██ | 2/10 [00:00<00:01, 6.88it/s]\n 30%|███ | 3/10 [00:00<00:00, 7.72it/s]\n 40%|████ | 4/10 [00:00<00:00, 7.88it/s]\n 50%|█████ | 5/10 [00:00<00:00, 8.00it/s]\n 60%|██████ | 6/10 [00:00<00:00, 8.29it/s]\n 70%|███████ | 7/10 [00:00<00:00, 8.27it/s]\n 80%|████████ | 8/10 [00:01<00:00, 8.24it/s]\n 90%|█████████ | 9/10 [00:01<00:00, 8.20it/s]\n100%|██████████| 10/10 [00:01<00:00, 8.12it/s]\n100%|██████████| 10/10 [00:01<00:00, 7.91it/s]\n 0%| | 0/30 [00:00<?, ?it/s]\n 3%|▎ | 1/30 [00:00<00:04, 6.81it/s]\n 10%|█ | 3/30 [00:00<00:02, 11.27it/s]\n 17%|█▋ | 5/30 [00:00<00:01, 12.72it/s]\n 23%|██▎ | 7/30 [00:00<00:01, 13.42it/s]\n 30%|███ | 9/30 [00:00<00:01, 13.82it/s]\n 37%|███▋ | 11/30 [00:00<00:01, 14.06it/s]\n 43%|████▎ | 13/30 [00:00<00:01, 14.19it/s]\n 50%|█████ | 15/30 [00:01<00:01, 14.30it/s]\n 57%|█████▋ | 17/30 [00:01<00:00, 14.37it/s]\n 63%|██████▎ | 19/30 [00:01<00:00, 14.42it/s]\n 70%|███████ | 21/30 [00:01<00:00, 14.42it/s]\n 77%|███████▋ | 23/30 [00:01<00:00, 14.44it/s]\n 83%|████████▎ | 25/30 [00:01<00:00, 14.47it/s]\n 90%|█████████ | 27/30 [00:01<00:00, 14.49it/s]\n 97%|█████████▋| 29/30 [00:02<00:00, 14.48it/s]\n100%|██████████| 30/30 [00:02<00:00, 13.98it/s]", "metrics": { "predict_time": 5.271856, "total_time": 9.743821 }, "output": [ "https://replicate.delivery/pbxt/J84fdfM92zuixEmX5feSvdvikPgaQoPCvxpdAAID6hJ0Ps4JB/out-0.png", "https://replicate.delivery/pbxt/RRyMMSv00eyNIKAyaq1C5RfayMZQeM7NhMzdsCJel7a0Ps4JB/out-1.png" ], "started_at": "2024-03-08T12:05:12.397757Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/pv6e4wtbf4xp6ec7chpdav3xve", "cancel": "https://api.replicate.com/v1/predictions/pv6e4wtbf4xp6ec7chpdav3xve/cancel" }, "version": "7c756b569b0e33bb3851fb303493105fb9d1637423ff0dbd00a4909bdd8dbe79" }
Generated inUsing seed: 6000 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a marble design tile, dark brown, glossy img2img mode 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:01, 5.22it/s] 20%|██ | 2/10 [00:00<00:01, 6.88it/s] 30%|███ | 3/10 [00:00<00:00, 7.72it/s] 40%|████ | 4/10 [00:00<00:00, 7.88it/s] 50%|█████ | 5/10 [00:00<00:00, 8.00it/s] 60%|██████ | 6/10 [00:00<00:00, 8.29it/s] 70%|███████ | 7/10 [00:00<00:00, 8.27it/s] 80%|████████ | 8/10 [00:01<00:00, 8.24it/s] 90%|█████████ | 9/10 [00:01<00:00, 8.20it/s] 100%|██████████| 10/10 [00:01<00:00, 8.12it/s] 100%|██████████| 10/10 [00:01<00:00, 7.91it/s] 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:04, 6.81it/s] 10%|█ | 3/30 [00:00<00:02, 11.27it/s] 17%|█▋ | 5/30 [00:00<00:01, 12.72it/s] 23%|██▎ | 7/30 [00:00<00:01, 13.42it/s] 30%|███ | 9/30 [00:00<00:01, 13.82it/s] 37%|███▋ | 11/30 [00:00<00:01, 14.06it/s] 43%|████▎ | 13/30 [00:00<00:01, 14.19it/s] 50%|█████ | 15/30 [00:01<00:01, 14.30it/s] 57%|█████▋ | 17/30 [00:01<00:00, 14.37it/s] 63%|██████▎ | 19/30 [00:01<00:00, 14.42it/s] 70%|███████ | 21/30 [00:01<00:00, 14.42it/s] 77%|███████▋ | 23/30 [00:01<00:00, 14.44it/s] 83%|████████▎ | 25/30 [00:01<00:00, 14.47it/s] 90%|█████████ | 27/30 [00:01<00:00, 14.49it/s] 97%|█████████▋| 29/30 [00:02<00:00, 14.48it/s] 100%|██████████| 30/30 [00:02<00:00, 13.98it/s]
Want to make some of these yourself?
Run this model