shahildhotre / sdxl-finetune-whiteclaw
- Public
- 37 runs
-
L40S
- SDXL fine-tune
Prediction
shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cfIDcxx8t9kyf9rgg0cgc0svj2b70cStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- white claw cans
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "white claw cans", "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 }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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", { input: { width: 1024, height: 1024, prompt: "white claw cans", 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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", input={ "width": 1024, "height": 1024, "prompt": "white claw cans", "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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", "input": { "width": 1024, "height": 1024, "prompt": "white claw cans", "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.
Output
{ "completed_at": "2024-06-28T18:55:28.515955Z", "created_at": "2024-06-28T18:55:05.850000Z", "data_removed": false, "error": null, "id": "cxx8t9kyf9rgg0cgc0svj2b70c", "input": { "width": 1024, "height": 1024, "prompt": "white claw cans", "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 }, "logs": "Using seed: 6337\nEnsuring enough disk space...\nFree disk space: 1732876619776\nDownloading weights: https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar\n2024-06-28T18:55:09Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3a601f772800c45d url=https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar\n2024-06-28T18:55:12Z | INFO | [ Complete ] dest=/src/weights-cache/3a601f772800c45d size=\"186 MB\" total_elapsed=2.974s url=https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar\nb''\nDownloaded weights in 3.123924493789673 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: white claw cans\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▏ | 1/50 [00:00<00:11, 4.22it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.22it/s]\n 6%|▌ | 3/50 [00:00<00:11, 4.23it/s]\n 8%|▊ | 4/50 [00:00<00:10, 4.23it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.22it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.21it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.21it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.21it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.21it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.21it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.21it/s]\n 24%|██▍ | 12/50 [00:02<00:09, 4.21it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.21it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.21it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.22it/s]\n 32%|███▏ | 16/50 [00:03<00:08, 4.21it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.20it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.20it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.20it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.21it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.21it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.21it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.21it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.20it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.21it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.20it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.20it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.21it/s]\n 58%|█████▊ | 29/50 [00:06<00:05, 4.20it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.20it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.19it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.19it/s]\n 66%|██████▌ | 33/50 [00:07<00:04, 4.19it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.19it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.20it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.20it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.19it/s]\n 76%|███████▌ | 38/50 [00:09<00:02, 4.19it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.19it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.19it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.19it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.19it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.19it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.19it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.19it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.20it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.19it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.19it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.19it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.19it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.20it/s]", "metrics": { "predict_time": 19.541705237, "total_time": 22.665955 }, "output": [ "https://replicate.delivery/pbxt/zsR8vhHFrnq3FxvF7ZI1wsI1IlkIHdOi9ceX6QtMTC5PylhJA/out-0.png" ], "started_at": "2024-06-28T18:55:08.974250Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/cxx8t9kyf9rgg0cgc0svj2b70c", "cancel": "https://api.replicate.com/v1/predictions/cxx8t9kyf9rgg0cgc0svj2b70c/cancel" }, "version": "8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf" }Generated inUsing seed: 6337 Ensuring enough disk space... Free disk space: 1732876619776 Downloading weights: https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar 2024-06-28T18:55:09Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3a601f772800c45d url=https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar 2024-06-28T18:55:12Z | INFO | [ Complete ] dest=/src/weights-cache/3a601f772800c45d size="186 MB" total_elapsed=2.974s url=https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar b'' Downloaded weights in 3.123924493789673 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: white claw cans txt2img mode 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▏ | 1/50 [00:00<00:11, 4.22it/s] 4%|▍ | 2/50 [00:00<00:11, 4.22it/s] 6%|▌ | 3/50 [00:00<00:11, 4.23it/s] 8%|▊ | 4/50 [00:00<00:10, 4.23it/s] 10%|█ | 5/50 [00:01<00:10, 4.22it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.21it/s] 14%|█▍ | 7/50 [00:01<00:10, 4.21it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.21it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.21it/s] 20%|██ | 10/50 [00:02<00:09, 4.21it/s] 22%|██▏ | 11/50 [00:02<00:09, 4.21it/s] 24%|██▍ | 12/50 [00:02<00:09, 4.21it/s] 26%|██▌ | 13/50 [00:03<00:08, 4.21it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.21it/s] 30%|███ | 15/50 [00:03<00:08, 4.22it/s] 32%|███▏ | 16/50 [00:03<00:08, 4.21it/s] 34%|███▍ | 17/50 [00:04<00:07, 4.20it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.20it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.20it/s] 40%|████ | 20/50 [00:04<00:07, 4.21it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.21it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.21it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.21it/s] 48%|████▊ | 24/50 [00:05<00:06, 4.20it/s] 50%|█████ | 25/50 [00:05<00:05, 4.21it/s] 52%|█████▏ | 26/50 [00:06<00:05, 4.20it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.20it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.21it/s] 58%|█████▊ | 29/50 [00:06<00:05, 4.20it/s] 60%|██████ | 30/50 [00:07<00:04, 4.20it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.19it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.19it/s] 66%|██████▌ | 33/50 [00:07<00:04, 4.19it/s] 68%|██████▊ | 34/50 [00:08<00:03, 4.19it/s] 70%|███████ | 35/50 [00:08<00:03, 4.20it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.20it/s] 74%|███████▍ | 37/50 [00:08<00:03, 4.19it/s] 76%|███████▌ | 38/50 [00:09<00:02, 4.19it/s] 78%|███████▊ | 39/50 [00:09<00:02, 4.19it/s] 80%|████████ | 40/50 [00:09<00:02, 4.19it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.19it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.19it/s] 86%|████████▌ | 43/50 [00:10<00:01, 4.19it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.19it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.19it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.20it/s] 94%|█████████▍| 47/50 [00:11<00:00, 4.19it/s] 96%|█████████▌| 48/50 [00:11<00:00, 4.19it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.19it/s] 100%|██████████| 50/50 [00:11<00:00, 4.19it/s] 100%|██████████| 50/50 [00:11<00:00, 4.20it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cfID4vb0y9cdmsrgj0cgc0vaenef28StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- white claw cans on football ground
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "white claw cans on football ground", "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 }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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", { input: { width: 1024, height: 1024, prompt: "white claw cans on football ground", 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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", input={ "width": 1024, "height": 1024, "prompt": "white claw cans on football ground", "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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", "input": { "width": 1024, "height": 1024, "prompt": "white claw cans on football ground", "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.
Output
{ "completed_at": "2024-06-28T18:59:16.418523Z", "created_at": "2024-06-28T18:58:26.342000Z", "data_removed": false, "error": null, "id": "4vb0y9cdmsrgj0cgc0vaenef28", "input": { "width": 1024, "height": 1024, "prompt": "white claw cans on football ground", "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 }, "logs": "Using seed: 28203\nEnsuring enough disk space...\nFree disk space: 1409171705856\nDownloading weights: https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar\n2024-06-28T18:58:53Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3a601f772800c45d url=https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar\n2024-06-28T18:58:59Z | INFO | [ Complete ] dest=/src/weights-cache/3a601f772800c45d size=\"186 MB\" total_elapsed=5.840s url=https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar\nb''\nDownloaded weights in 6.010019779205322 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: white claw cans on football ground\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▏ | 1/50 [00:00<00:12, 3.86it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.08it/s]\n 6%|▌ | 3/50 [00:00<00:11, 4.16it/s]\n 8%|▊ | 4/50 [00:00<00:10, 4.20it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.21it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.22it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.22it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.22it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.23it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.22it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.23it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.23it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.24it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.23it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.23it/s]\n 32%|███▏ | 16/50 [00:03<00:08, 4.23it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.23it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.23it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.22it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.23it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.24it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.24it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.25it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.25it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.25it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.25it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.25it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.25it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.25it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.25it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.25it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.25it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.26it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.25it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.25it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.25it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.25it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.25it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.25it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.25it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.25it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.25it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.25it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.25it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.25it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.25it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.25it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.25it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.24it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.24it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.24it/s]", "metrics": { "predict_time": 22.838852834, "total_time": 50.076523 }, "output": [ "https://replicate.delivery/pbxt/5LaA6pwBmgZOBdFIMnI08tS9y1HR0OK0LDe88eWcJFZCoLDTA/out-0.png" ], "started_at": "2024-06-28T18:58:53.579670Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/4vb0y9cdmsrgj0cgc0vaenef28", "cancel": "https://api.replicate.com/v1/predictions/4vb0y9cdmsrgj0cgc0vaenef28/cancel" }, "version": "8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf" }Generated inUsing seed: 28203 Ensuring enough disk space... Free disk space: 1409171705856 Downloading weights: https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar 2024-06-28T18:58:53Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3a601f772800c45d url=https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar 2024-06-28T18:58:59Z | INFO | [ Complete ] dest=/src/weights-cache/3a601f772800c45d size="186 MB" total_elapsed=5.840s url=https://replicate.delivery/pbxt/rwvzo0hcN0IWNdZCgfbpizCVnYZH6X7BSjGZLgdFfFvwjLDTA/trained_model.tar b'' Downloaded weights in 6.010019779205322 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: white claw cans on football ground txt2img mode 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▏ | 1/50 [00:00<00:12, 3.86it/s] 4%|▍ | 2/50 [00:00<00:11, 4.08it/s] 6%|▌ | 3/50 [00:00<00:11, 4.16it/s] 8%|▊ | 4/50 [00:00<00:10, 4.20it/s] 10%|█ | 5/50 [00:01<00:10, 4.21it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.22it/s] 14%|█▍ | 7/50 [00:01<00:10, 4.22it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.22it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.23it/s] 20%|██ | 10/50 [00:02<00:09, 4.22it/s] 22%|██▏ | 11/50 [00:02<00:09, 4.23it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.23it/s] 26%|██▌ | 13/50 [00:03<00:08, 4.24it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.23it/s] 30%|███ | 15/50 [00:03<00:08, 4.23it/s] 32%|███▏ | 16/50 [00:03<00:08, 4.23it/s] 34%|███▍ | 17/50 [00:04<00:07, 4.23it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.23it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.22it/s] 40%|████ | 20/50 [00:04<00:07, 4.23it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.24it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.24it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.25it/s] 48%|████▊ | 24/50 [00:05<00:06, 4.25it/s] 50%|█████ | 25/50 [00:05<00:05, 4.25it/s] 52%|█████▏ | 26/50 [00:06<00:05, 4.25it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.25it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.25it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.25it/s] 60%|██████ | 30/50 [00:07<00:04, 4.25it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.25it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.25it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.26it/s] 68%|██████▊ | 34/50 [00:08<00:03, 4.25it/s] 70%|███████ | 35/50 [00:08<00:03, 4.25it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.25it/s] 74%|███████▍ | 37/50 [00:08<00:03, 4.25it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.25it/s] 78%|███████▊ | 39/50 [00:09<00:02, 4.25it/s] 80%|████████ | 40/50 [00:09<00:02, 4.25it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.25it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.25it/s] 86%|████████▌ | 43/50 [00:10<00:01, 4.25it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.25it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.25it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.25it/s] 94%|█████████▍| 47/50 [00:11<00:00, 4.25it/s] 96%|█████████▌| 48/50 [00:11<00:00, 4.25it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.24it/s] 100%|██████████| 50/50 [00:11<00:00, 4.24it/s] 100%|██████████| 50/50 [00:11<00:00, 4.24it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cfID169z7ztst9rgj0cgc15bcp9csgStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- kpop artist on football ground with white claw cans
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "kpop artist on football ground with white claw cans", "refine": "expert_ensemble_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 }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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", { input: { width: 1024, height: 1024, prompt: "kpop artist on football ground with white claw cans", refine: "expert_ensemble_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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", input={ "width": 1024, "height": 1024, "prompt": "kpop artist on football ground with white claw cans", "refine": "expert_ensemble_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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", "input": { "width": 1024, "height": 1024, "prompt": "kpop artist on football ground with white claw cans", "refine": "expert_ensemble_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.
Output
{ "completed_at": "2024-06-28T19:20:22.012435Z", "created_at": "2024-06-28T19:20:03.794000Z", "data_removed": false, "error": null, "id": "169z7ztst9rgj0cgc15bcp9csg", "input": { "width": 1024, "height": 1024, "prompt": "kpop artist on football ground with white claw cans", "refine": "expert_ensemble_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 }, "logs": "Using seed: 51151\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: kpop artist on football ground with white claw cans\ntxt2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:09, 4.22it/s]\n 5%|▌ | 2/40 [00:00<00:09, 4.22it/s]\n 8%|▊ | 3/40 [00:00<00:08, 4.22it/s]\n 10%|█ | 4/40 [00:00<00:08, 4.21it/s]\n 12%|█▎ | 5/40 [00:01<00:08, 4.20it/s]\n 15%|█▌ | 6/40 [00:01<00:08, 4.20it/s]\n 18%|█▊ | 7/40 [00:01<00:07, 4.20it/s]\n 20%|██ | 8/40 [00:01<00:07, 4.20it/s]\n 22%|██▎ | 9/40 [00:02<00:07, 4.20it/s]\n 25%|██▌ | 10/40 [00:02<00:07, 4.20it/s]\n 28%|██▊ | 11/40 [00:02<00:06, 4.20it/s]\n 30%|███ | 12/40 [00:02<00:06, 4.20it/s]\n 32%|███▎ | 13/40 [00:03<00:06, 4.20it/s]\n 35%|███▌ | 14/40 [00:03<00:06, 4.19it/s]\n 38%|███▊ | 15/40 [00:03<00:05, 4.19it/s]\n 40%|████ | 16/40 [00:03<00:05, 4.19it/s]\n 42%|████▎ | 17/40 [00:04<00:05, 4.19it/s]\n 45%|████▌ | 18/40 [00:04<00:05, 4.18it/s]\n 48%|████▊ | 19/40 [00:04<00:05, 4.18it/s]\n 50%|█████ | 20/40 [00:04<00:04, 4.19it/s]\n 52%|█████▎ | 21/40 [00:05<00:04, 4.18it/s]\n 55%|█████▌ | 22/40 [00:05<00:04, 4.18it/s]\n 57%|█████▊ | 23/40 [00:05<00:04, 4.18it/s]\n 60%|██████ | 24/40 [00:05<00:03, 4.18it/s]\n 62%|██████▎ | 25/40 [00:05<00:03, 4.18it/s]\n 65%|██████▌ | 26/40 [00:06<00:03, 4.18it/s]\n 68%|██████▊ | 27/40 [00:06<00:03, 4.17it/s]\n 70%|███████ | 28/40 [00:06<00:02, 4.17it/s]\n 72%|███████▎ | 29/40 [00:06<00:02, 4.17it/s]\n 75%|███████▌ | 30/40 [00:07<00:02, 4.17it/s]\n 78%|███████▊ | 31/40 [00:07<00:02, 4.17it/s]\n 80%|████████ | 32/40 [00:07<00:01, 4.17it/s]\n 82%|████████▎ | 33/40 [00:07<00:01, 4.17it/s]\n 85%|████████▌ | 34/40 [00:08<00:01, 4.17it/s]\n 88%|████████▊ | 35/40 [00:08<00:01, 4.17it/s]\n 90%|█████████ | 36/40 [00:08<00:00, 4.17it/s]\n 92%|█████████▎| 37/40 [00:08<00:00, 4.17it/s]\n 95%|█████████▌| 38/40 [00:09<00:00, 4.17it/s]\n 98%|█████████▊| 39/40 [00:09<00:00, 4.17it/s]\n100%|██████████| 40/40 [00:09<00:00, 4.18it/s]\n100%|██████████| 40/40 [00:09<00:00, 4.18it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 4.22it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.21it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.21it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.18it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.19it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.19it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.18it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.17it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.16it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.17it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.18it/s]", "metrics": { "predict_time": 16.530744255, "total_time": 18.218435 }, "output": [ "https://replicate.delivery/pbxt/CYHPa1IdpnK5C5wBmjnxxeF9KHUa7JGTQjxTAek2Eil07LDTA/out-0.png" ], "started_at": "2024-06-28T19:20:05.481690Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/169z7ztst9rgj0cgc15bcp9csg", "cancel": "https://api.replicate.com/v1/predictions/169z7ztst9rgj0cgc15bcp9csg/cancel" }, "version": "8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf" }Generated inUsing seed: 51151 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: kpop artist on football ground with white claw cans txt2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:09, 4.22it/s] 5%|▌ | 2/40 [00:00<00:09, 4.22it/s] 8%|▊ | 3/40 [00:00<00:08, 4.22it/s] 10%|█ | 4/40 [00:00<00:08, 4.21it/s] 12%|█▎ | 5/40 [00:01<00:08, 4.20it/s] 15%|█▌ | 6/40 [00:01<00:08, 4.20it/s] 18%|█▊ | 7/40 [00:01<00:07, 4.20it/s] 20%|██ | 8/40 [00:01<00:07, 4.20it/s] 22%|██▎ | 9/40 [00:02<00:07, 4.20it/s] 25%|██▌ | 10/40 [00:02<00:07, 4.20it/s] 28%|██▊ | 11/40 [00:02<00:06, 4.20it/s] 30%|███ | 12/40 [00:02<00:06, 4.20it/s] 32%|███▎ | 13/40 [00:03<00:06, 4.20it/s] 35%|███▌ | 14/40 [00:03<00:06, 4.19it/s] 38%|███▊ | 15/40 [00:03<00:05, 4.19it/s] 40%|████ | 16/40 [00:03<00:05, 4.19it/s] 42%|████▎ | 17/40 [00:04<00:05, 4.19it/s] 45%|████▌ | 18/40 [00:04<00:05, 4.18it/s] 48%|████▊ | 19/40 [00:04<00:05, 4.18it/s] 50%|█████ | 20/40 [00:04<00:04, 4.19it/s] 52%|█████▎ | 21/40 [00:05<00:04, 4.18it/s] 55%|█████▌ | 22/40 [00:05<00:04, 4.18it/s] 57%|█████▊ | 23/40 [00:05<00:04, 4.18it/s] 60%|██████ | 24/40 [00:05<00:03, 4.18it/s] 62%|██████▎ | 25/40 [00:05<00:03, 4.18it/s] 65%|██████▌ | 26/40 [00:06<00:03, 4.18it/s] 68%|██████▊ | 27/40 [00:06<00:03, 4.17it/s] 70%|███████ | 28/40 [00:06<00:02, 4.17it/s] 72%|███████▎ | 29/40 [00:06<00:02, 4.17it/s] 75%|███████▌ | 30/40 [00:07<00:02, 4.17it/s] 78%|███████▊ | 31/40 [00:07<00:02, 4.17it/s] 80%|████████ | 32/40 [00:07<00:01, 4.17it/s] 82%|████████▎ | 33/40 [00:07<00:01, 4.17it/s] 85%|████████▌ | 34/40 [00:08<00:01, 4.17it/s] 88%|████████▊ | 35/40 [00:08<00:01, 4.17it/s] 90%|█████████ | 36/40 [00:08<00:00, 4.17it/s] 92%|█████████▎| 37/40 [00:08<00:00, 4.17it/s] 95%|█████████▌| 38/40 [00:09<00:00, 4.17it/s] 98%|█████████▊| 39/40 [00:09<00:00, 4.17it/s] 100%|██████████| 40/40 [00:09<00:00, 4.18it/s] 100%|██████████| 40/40 [00:09<00:00, 4.18it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 4.22it/s] 20%|██ | 2/10 [00:00<00:01, 4.21it/s] 30%|███ | 3/10 [00:00<00:01, 4.21it/s] 40%|████ | 4/10 [00:00<00:01, 4.18it/s] 50%|█████ | 5/10 [00:01<00:01, 4.19it/s] 60%|██████ | 6/10 [00:01<00:00, 4.19it/s] 70%|███████ | 7/10 [00:01<00:00, 4.18it/s] 80%|████████ | 8/10 [00:01<00:00, 4.17it/s] 90%|█████████ | 9/10 [00:02<00:00, 4.16it/s] 100%|██████████| 10/10 [00:02<00:00, 4.17it/s] 100%|██████████| 10/10 [00:02<00:00, 4.18it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cfIDmaf91r0x3xrgm0cgc16andnh0gStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- kpop artists in background on football ground with white claw can
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "kpop artists in background on football ground with white claw can", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", { input: { width: 1024, height: 1024, prompt: "kpop artists in background on football ground with white claw can", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, 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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", input={ "width": 1024, "height": 1024, "prompt": "kpop artists in background on football ground with white claw can", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf", "input": { "width": 1024, "height": 1024, "prompt": "kpop artists in background on football ground with white claw can", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "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.
Output
{ "completed_at": "2024-06-28T19:22:15.977375Z", "created_at": "2024-06-28T19:21:59.327000Z", "data_removed": false, "error": null, "id": "maf91r0x3xrgm0cgc16andnh0g", "input": { "width": 1024, "height": 1024, "prompt": "kpop artists in background on football ground with white claw can", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 34237\nskipping loading .. weights already loaded\nPrompt: kpop artists in background on football ground with white claw can\ntxt2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:09, 4.20it/s]\n 5%|▌ | 2/40 [00:00<00:09, 4.20it/s]\n 8%|▊ | 3/40 [00:00<00:08, 4.21it/s]\n 10%|█ | 4/40 [00:00<00:08, 4.20it/s]\n 12%|█▎ | 5/40 [00:01<00:08, 4.19it/s]\n 15%|█▌ | 6/40 [00:01<00:08, 4.19it/s]\n 18%|█▊ | 7/40 [00:01<00:07, 4.19it/s]\n 20%|██ | 8/40 [00:01<00:07, 4.19it/s]\n 22%|██▎ | 9/40 [00:02<00:07, 4.19it/s]\n 25%|██▌ | 10/40 [00:02<00:07, 4.18it/s]\n 28%|██▊ | 11/40 [00:02<00:06, 4.18it/s]\n 30%|███ | 12/40 [00:02<00:06, 4.18it/s]\n 32%|███▎ | 13/40 [00:03<00:06, 4.17it/s]\n 35%|███▌ | 14/40 [00:03<00:06, 4.18it/s]\n 38%|███▊ | 15/40 [00:03<00:05, 4.17it/s]\n 40%|████ | 16/40 [00:03<00:05, 4.17it/s]\n 42%|████▎ | 17/40 [00:04<00:05, 4.17it/s]\n 45%|████▌ | 18/40 [00:04<00:05, 4.17it/s]\n 48%|████▊ | 19/40 [00:04<00:05, 4.16it/s]\n 50%|█████ | 20/40 [00:04<00:04, 4.17it/s]\n 52%|█████▎ | 21/40 [00:05<00:04, 4.16it/s]\n 55%|█████▌ | 22/40 [00:05<00:04, 4.16it/s]\n 57%|█████▊ | 23/40 [00:05<00:04, 4.16it/s]\n 60%|██████ | 24/40 [00:05<00:03, 4.16it/s]\n 62%|██████▎ | 25/40 [00:05<00:03, 4.16it/s]\n 65%|██████▌ | 26/40 [00:06<00:03, 4.16it/s]\n 68%|██████▊ | 27/40 [00:06<00:03, 4.16it/s]\n 70%|███████ | 28/40 [00:06<00:02, 4.16it/s]\n 72%|███████▎ | 29/40 [00:06<00:02, 4.16it/s]\n 75%|███████▌ | 30/40 [00:07<00:02, 4.16it/s]\n 78%|███████▊ | 31/40 [00:07<00:02, 4.16it/s]\n 80%|████████ | 32/40 [00:07<00:01, 4.16it/s]\n 82%|████████▎ | 33/40 [00:07<00:01, 4.16it/s]\n 85%|████████▌ | 34/40 [00:08<00:01, 4.16it/s]\n 88%|████████▊ | 35/40 [00:08<00:01, 4.16it/s]\n 90%|█████████ | 36/40 [00:08<00:00, 4.16it/s]\n 92%|█████████▎| 37/40 [00:08<00:00, 4.15it/s]\n 95%|█████████▌| 38/40 [00:09<00:00, 4.15it/s]\n 98%|█████████▊| 39/40 [00:09<00:00, 4.15it/s]\n100%|██████████| 40/40 [00:09<00:00, 4.16it/s]\n100%|██████████| 40/40 [00:09<00:00, 4.17it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 4.22it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.18it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.17it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.15it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.15it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.16it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.16it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.15it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.15it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.15it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.16it/s]", "metrics": { "predict_time": 14.569512118, "total_time": 16.650375 }, "output": [ "https://replicate.delivery/pbxt/3N91VYeBYASaZyK8JxeByjhHfICip6j0Fqd0VGWwVeDZ2vMMB/out-0.png" ], "started_at": "2024-06-28T19:22:01.407862Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/maf91r0x3xrgm0cgc16andnh0g", "cancel": "https://api.replicate.com/v1/predictions/maf91r0x3xrgm0cgc16andnh0g/cancel" }, "version": "8ead60620ef130afb844f351e95777224e05a2792c221089461869ee9e4385cf" }Generated inUsing seed: 34237 skipping loading .. weights already loaded Prompt: kpop artists in background on football ground with white claw can txt2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:09, 4.20it/s] 5%|▌ | 2/40 [00:00<00:09, 4.20it/s] 8%|▊ | 3/40 [00:00<00:08, 4.21it/s] 10%|█ | 4/40 [00:00<00:08, 4.20it/s] 12%|█▎ | 5/40 [00:01<00:08, 4.19it/s] 15%|█▌ | 6/40 [00:01<00:08, 4.19it/s] 18%|█▊ | 7/40 [00:01<00:07, 4.19it/s] 20%|██ | 8/40 [00:01<00:07, 4.19it/s] 22%|██▎ | 9/40 [00:02<00:07, 4.19it/s] 25%|██▌ | 10/40 [00:02<00:07, 4.18it/s] 28%|██▊ | 11/40 [00:02<00:06, 4.18it/s] 30%|███ | 12/40 [00:02<00:06, 4.18it/s] 32%|███▎ | 13/40 [00:03<00:06, 4.17it/s] 35%|███▌ | 14/40 [00:03<00:06, 4.18it/s] 38%|███▊ | 15/40 [00:03<00:05, 4.17it/s] 40%|████ | 16/40 [00:03<00:05, 4.17it/s] 42%|████▎ | 17/40 [00:04<00:05, 4.17it/s] 45%|████▌ | 18/40 [00:04<00:05, 4.17it/s] 48%|████▊ | 19/40 [00:04<00:05, 4.16it/s] 50%|█████ | 20/40 [00:04<00:04, 4.17it/s] 52%|█████▎ | 21/40 [00:05<00:04, 4.16it/s] 55%|█████▌ | 22/40 [00:05<00:04, 4.16it/s] 57%|█████▊ | 23/40 [00:05<00:04, 4.16it/s] 60%|██████ | 24/40 [00:05<00:03, 4.16it/s] 62%|██████▎ | 25/40 [00:05<00:03, 4.16it/s] 65%|██████▌ | 26/40 [00:06<00:03, 4.16it/s] 68%|██████▊ | 27/40 [00:06<00:03, 4.16it/s] 70%|███████ | 28/40 [00:06<00:02, 4.16it/s] 72%|███████▎ | 29/40 [00:06<00:02, 4.16it/s] 75%|███████▌ | 30/40 [00:07<00:02, 4.16it/s] 78%|███████▊ | 31/40 [00:07<00:02, 4.16it/s] 80%|████████ | 32/40 [00:07<00:01, 4.16it/s] 82%|████████▎ | 33/40 [00:07<00:01, 4.16it/s] 85%|████████▌ | 34/40 [00:08<00:01, 4.16it/s] 88%|████████▊ | 35/40 [00:08<00:01, 4.16it/s] 90%|█████████ | 36/40 [00:08<00:00, 4.16it/s] 92%|█████████▎| 37/40 [00:08<00:00, 4.15it/s] 95%|█████████▌| 38/40 [00:09<00:00, 4.15it/s] 98%|█████████▊| 39/40 [00:09<00:00, 4.15it/s] 100%|██████████| 40/40 [00:09<00:00, 4.16it/s] 100%|██████████| 40/40 [00:09<00:00, 4.17it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 4.22it/s] 20%|██ | 2/10 [00:00<00:01, 4.18it/s] 30%|███ | 3/10 [00:00<00:01, 4.17it/s] 40%|████ | 4/10 [00:00<00:01, 4.15it/s] 50%|█████ | 5/10 [00:01<00:01, 4.15it/s] 60%|██████ | 6/10 [00:01<00:00, 4.16it/s] 70%|███████ | 7/10 [00:01<00:00, 4.16it/s] 80%|████████ | 8/10 [00:01<00:00, 4.15it/s] 90%|█████████ | 9/10 [00:02<00:00, 4.15it/s] 100%|██████████| 10/10 [00:02<00:00, 4.15it/s] 100%|██████████| 10/10 [00:02<00:00, 4.16it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:22c841f547d88c3e56647a7a0ba0f1e7c6e47085057aa2172f342aa0ec09bf31IDebmhjvsb5drgg0cgbqetfktr0mStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- whiteclaw, football
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "whiteclaw, football", "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 }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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:22c841f547d88c3e56647a7a0ba0f1e7c6e47085057aa2172f342aa0ec09bf31", { input: { width: 1024, height: 1024, prompt: "whiteclaw, football", 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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:22c841f547d88c3e56647a7a0ba0f1e7c6e47085057aa2172f342aa0ec09bf31", input={ "width": 1024, "height": 1024, "prompt": "whiteclaw, football", "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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:22c841f547d88c3e56647a7a0ba0f1e7c6e47085057aa2172f342aa0ec09bf31", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaw, football", "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.
Output
{ "completed_at": "2024-06-28T08:01:56.407551Z", "created_at": "2024-06-28T08:01:33.995000Z", "data_removed": false, "error": null, "id": "ebmhjvsb5drgg0cgbqetfktr0m", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaw, football", "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 }, "logs": "Using seed: 37073\nEnsuring enough disk space...\nFree disk space: 1553943666688\nDownloading weights: https://replicate.delivery/pbxt/mqkY09biR0LfRSqJINfMgHDipgcyY832NSB5fkGEATHd2DGmA/trained_model.tar\n2024-06-28T08:01:35Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/6fba1273a53b7ec5 url=https://replicate.delivery/pbxt/mqkY09biR0LfRSqJINfMgHDipgcyY832NSB5fkGEATHd2DGmA/trained_model.tar\n2024-06-28T08:01:41Z | INFO | [ Complete ] dest=/src/weights-cache/6fba1273a53b7ec5 size=\"186 MB\" total_elapsed=1.246s url=https://replicate.delivery/pbxt/mqkY09biR0LfRSqJINfMgHDipgcyY832NSB5fkGEATHd2DGmA/trained_model.tar\nb''\nDownloaded weights in 6.318415403366089 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: whiteclaw, football\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)\nreturn F.conv2d(input, weight, bias, self.stride,\n/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▏ | 1/50 [00:00<00:20, 2.36it/s]\n 4%|▍ | 2/50 [00:00<00:15, 3.20it/s]\n 6%|▌ | 3/50 [00:00<00:13, 3.60it/s]\n 8%|▊ | 4/50 [00:01<00:12, 3.83it/s]\n 10%|█ | 5/50 [00:01<00:11, 3.96it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.05it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.11it/s]\n 16%|█▌ | 8/50 [00:02<00:10, 4.15it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.18it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.19it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.20it/s]\n 24%|██▍ | 12/50 [00:03<00:09, 4.21it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.21it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.21it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.22it/s]\n 32%|███▏ | 16/50 [00:03<00:08, 4.22it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.22it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.22it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.23it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.22it/s]\n 42%|████▏ | 21/50 [00:05<00:06, 4.22it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.22it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.22it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.22it/s]\n 50%|█████ | 25/50 [00:06<00:05, 4.22it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.21it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.22it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.22it/s]\n 58%|█████▊ | 29/50 [00:07<00:04, 4.23it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.24it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.23it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.24it/s]\n 66%|██████▌ | 33/50 [00:07<00:04, 4.24it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.25it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.25it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.25it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.25it/s]\n 76%|███████▌ | 38/50 [00:09<00:02, 4.24it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.25it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.23it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.23it/s]\n 84%|████████▍ | 42/50 [00:10<00:01, 4.24it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.24it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.24it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.24it/s]\n 92%|█████████▏| 46/50 [00:11<00:00, 4.24it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.24it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.24it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.24it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.24it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.17it/s]", "metrics": { "predict_time": 21.067537381, "total_time": 22.412551 }, "output": [ "https://replicate.delivery/pbxt/mQRSV5nCdiYxKNrBeMPMmOzlfxVxQhE5cSv3SAOjiLI0fDGmA/out-0.png" ], "started_at": "2024-06-28T08:01:35.340014Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/ebmhjvsb5drgg0cgbqetfktr0m", "cancel": "https://api.replicate.com/v1/predictions/ebmhjvsb5drgg0cgbqetfktr0m/cancel" }, "version": "22c841f547d88c3e56647a7a0ba0f1e7c6e47085057aa2172f342aa0ec09bf31" }Generated inUsing seed: 37073 Ensuring enough disk space... Free disk space: 1553943666688 Downloading weights: https://replicate.delivery/pbxt/mqkY09biR0LfRSqJINfMgHDipgcyY832NSB5fkGEATHd2DGmA/trained_model.tar 2024-06-28T08:01:35Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/6fba1273a53b7ec5 url=https://replicate.delivery/pbxt/mqkY09biR0LfRSqJINfMgHDipgcyY832NSB5fkGEATHd2DGmA/trained_model.tar 2024-06-28T08:01:41Z | INFO | [ Complete ] dest=/src/weights-cache/6fba1273a53b7ec5 size="186 MB" total_elapsed=1.246s url=https://replicate.delivery/pbxt/mqkY09biR0LfRSqJINfMgHDipgcyY832NSB5fkGEATHd2DGmA/trained_model.tar b'' Downloaded weights in 6.318415403366089 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: whiteclaw, football txt2img mode 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.) return F.conv2d(input, weight, bias, self.stride, /usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▏ | 1/50 [00:00<00:20, 2.36it/s] 4%|▍ | 2/50 [00:00<00:15, 3.20it/s] 6%|▌ | 3/50 [00:00<00:13, 3.60it/s] 8%|▊ | 4/50 [00:01<00:12, 3.83it/s] 10%|█ | 5/50 [00:01<00:11, 3.96it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.05it/s] 14%|█▍ | 7/50 [00:01<00:10, 4.11it/s] 16%|█▌ | 8/50 [00:02<00:10, 4.15it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.18it/s] 20%|██ | 10/50 [00:02<00:09, 4.19it/s] 22%|██▏ | 11/50 [00:02<00:09, 4.20it/s] 24%|██▍ | 12/50 [00:03<00:09, 4.21it/s] 26%|██▌ | 13/50 [00:03<00:08, 4.21it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.21it/s] 30%|███ | 15/50 [00:03<00:08, 4.22it/s] 32%|███▏ | 16/50 [00:03<00:08, 4.22it/s] 34%|███▍ | 17/50 [00:04<00:07, 4.22it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.22it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.23it/s] 40%|████ | 20/50 [00:04<00:07, 4.22it/s] 42%|████▏ | 21/50 [00:05<00:06, 4.22it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.22it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.22it/s] 48%|████▊ | 24/50 [00:05<00:06, 4.22it/s] 50%|█████ | 25/50 [00:06<00:05, 4.22it/s] 52%|█████▏ | 26/50 [00:06<00:05, 4.21it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.22it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.22it/s] 58%|█████▊ | 29/50 [00:07<00:04, 4.23it/s] 60%|██████ | 30/50 [00:07<00:04, 4.24it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.23it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.24it/s] 66%|██████▌ | 33/50 [00:07<00:04, 4.24it/s] 68%|██████▊ | 34/50 [00:08<00:03, 4.25it/s] 70%|███████ | 35/50 [00:08<00:03, 4.25it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.25it/s] 74%|███████▍ | 37/50 [00:08<00:03, 4.25it/s] 76%|███████▌ | 38/50 [00:09<00:02, 4.24it/s] 78%|███████▊ | 39/50 [00:09<00:02, 4.25it/s] 80%|████████ | 40/50 [00:09<00:02, 4.23it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.23it/s] 84%|████████▍ | 42/50 [00:10<00:01, 4.24it/s] 86%|████████▌ | 43/50 [00:10<00:01, 4.24it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.24it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.24it/s] 92%|█████████▏| 46/50 [00:11<00:00, 4.24it/s] 94%|█████████▍| 47/50 [00:11<00:00, 4.24it/s] 96%|█████████▌| 48/50 [00:11<00:00, 4.24it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.24it/s] 100%|██████████| 50/50 [00:11<00:00, 4.24it/s] 100%|██████████| 50/50 [00:11<00:00, 4.17it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681cID821g3nn4psrgp0cgbqst3x2vtcStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- white claw cans
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "white claw cans", "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 }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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", { input: { width: 1024, height: 1024, prompt: "white claw cans", 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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", input={ "width": 1024, "height": 1024, "prompt": "white claw cans", "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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", "input": { "width": 1024, "height": 1024, "prompt": "white claw cans", "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.
Output
{ "completed_at": "2024-06-28T08:26:29.042769Z", "created_at": "2024-06-28T08:26:06.902000Z", "data_removed": false, "error": null, "id": "821g3nn4psrgp0cgbqst3x2vtc", "input": { "width": 1024, "height": 1024, "prompt": "white claw cans", "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 }, "logs": "Using seed: 31155\nEnsuring enough disk space...\nFree disk space: 1438424616960\nDownloading weights: https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\n2024-06-28T08:26:11Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2e43e1cc9cefbe1d url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\n2024-06-28T08:26:13Z | INFO | [ Complete ] dest=/src/weights-cache/2e43e1cc9cefbe1d size=\"186 MB\" total_elapsed=1.751s url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\nb''\nDownloaded weights in 1.8748784065246582 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: white claw cans\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▏ | 1/50 [00:00<00:11, 4.27it/s]\n 4%|▍ | 2/50 [00:00<00:11, 4.26it/s]\n 6%|▌ | 3/50 [00:00<00:11, 4.25it/s]\n 8%|▊ | 4/50 [00:00<00:10, 4.25it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.24it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.24it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.25it/s]\n 16%|█▌ | 8/50 [00:01<00:09, 4.25it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.25it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.24it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.25it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.25it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.25it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.25it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.26it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.26it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.25it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.25it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.25it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.24it/s]\n 42%|████▏ | 21/50 [00:04<00:06, 4.24it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.25it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.25it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.25it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.25it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.25it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.25it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.25it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.25it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.25it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.24it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.24it/s]\n 66%|██████▌ | 33/50 [00:07<00:04, 4.24it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.24it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.24it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.25it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.25it/s]\n 76%|███████▌ | 38/50 [00:08<00:02, 4.24it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.24it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.23it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.23it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.23it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.23it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.23it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.23it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.23it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.23it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.23it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.23it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.23it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.24it/s]", "metrics": { "predict_time": 17.580557212, "total_time": 22.140769 }, "output": [ "https://replicate.delivery/pbxt/9LwItAe8gwVOeEiglIJAmUTBRs3kKqKaKbefjiLz7qiSbJMMB/out-0.png" ], "started_at": "2024-06-28T08:26:11.462212Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/821g3nn4psrgp0cgbqst3x2vtc", "cancel": "https://api.replicate.com/v1/predictions/821g3nn4psrgp0cgbqst3x2vtc/cancel" }, "version": "9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c" }Generated inUsing seed: 31155 Ensuring enough disk space... Free disk space: 1438424616960 Downloading weights: https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar 2024-06-28T08:26:11Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2e43e1cc9cefbe1d url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar 2024-06-28T08:26:13Z | INFO | [ Complete ] dest=/src/weights-cache/2e43e1cc9cefbe1d size="186 MB" total_elapsed=1.751s url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar b'' Downloaded weights in 1.8748784065246582 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: white claw cans txt2img mode 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▏ | 1/50 [00:00<00:11, 4.27it/s] 4%|▍ | 2/50 [00:00<00:11, 4.26it/s] 6%|▌ | 3/50 [00:00<00:11, 4.25it/s] 8%|▊ | 4/50 [00:00<00:10, 4.25it/s] 10%|█ | 5/50 [00:01<00:10, 4.24it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.24it/s] 14%|█▍ | 7/50 [00:01<00:10, 4.25it/s] 16%|█▌ | 8/50 [00:01<00:09, 4.25it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.25it/s] 20%|██ | 10/50 [00:02<00:09, 4.24it/s] 22%|██▏ | 11/50 [00:02<00:09, 4.25it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.25it/s] 26%|██▌ | 13/50 [00:03<00:08, 4.25it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.25it/s] 30%|███ | 15/50 [00:03<00:08, 4.26it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.26it/s] 34%|███▍ | 17/50 [00:04<00:07, 4.25it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.25it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.25it/s] 40%|████ | 20/50 [00:04<00:07, 4.24it/s] 42%|████▏ | 21/50 [00:04<00:06, 4.24it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.25it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.25it/s] 48%|████▊ | 24/50 [00:05<00:06, 4.25it/s] 50%|█████ | 25/50 [00:05<00:05, 4.25it/s] 52%|█████▏ | 26/50 [00:06<00:05, 4.25it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.25it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.25it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.25it/s] 60%|██████ | 30/50 [00:07<00:04, 4.25it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.24it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.24it/s] 66%|██████▌ | 33/50 [00:07<00:04, 4.24it/s] 68%|██████▊ | 34/50 [00:08<00:03, 4.24it/s] 70%|███████ | 35/50 [00:08<00:03, 4.24it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.25it/s] 74%|███████▍ | 37/50 [00:08<00:03, 4.25it/s] 76%|███████▌ | 38/50 [00:08<00:02, 4.24it/s] 78%|███████▊ | 39/50 [00:09<00:02, 4.24it/s] 80%|████████ | 40/50 [00:09<00:02, 4.23it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.23it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.23it/s] 86%|████████▌ | 43/50 [00:10<00:01, 4.23it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.23it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.23it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.23it/s] 94%|█████████▍| 47/50 [00:11<00:00, 4.23it/s] 96%|█████████▌| 48/50 [00:11<00:00, 4.23it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.23it/s] 100%|██████████| 50/50 [00:11<00:00, 4.23it/s] 100%|██████████| 50/50 [00:11<00:00, 4.24it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681cID1vgww2bbm1rgp0cgbqysfxncxrStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- whiteclaws cans in football ground
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "whiteclaws cans in football ground", "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 }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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", { input: { width: 1024, height: 1024, prompt: "whiteclaws cans in football ground", 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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", input={ "width": 1024, "height": 1024, "prompt": "whiteclaws cans in football ground", "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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaws cans in football ground", "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.
Output
{ "completed_at": "2024-06-28T08:37:07.426689Z", "created_at": "2024-06-28T08:36:47.648000Z", "data_removed": false, "error": null, "id": "1vgww2bbm1rgp0cgbqysfxncxr", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaws cans in football ground", "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 }, "logs": "Using seed: 7336\nEnsuring enough disk space...\nFree disk space: 1791625609216\nDownloading weights: https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\n2024-06-28T08:36:50Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2e43e1cc9cefbe1d url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\n2024-06-28T08:36:51Z | INFO | [ Complete ] dest=/src/weights-cache/2e43e1cc9cefbe1d size=\"186 MB\" total_elapsed=1.159s url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\nb''\nDownloaded weights in 1.3218357563018799 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: whiteclaws cans in football ground\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▏ | 1/50 [00:00<00:13, 3.68it/s]\n 4%|▍ | 2/50 [00:00<00:12, 3.96it/s]\n 6%|▌ | 3/50 [00:00<00:11, 4.06it/s]\n 8%|▊ | 4/50 [00:00<00:11, 4.12it/s]\n 10%|█ | 5/50 [00:01<00:10, 4.16it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.18it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.19it/s]\n 16%|█▌ | 8/50 [00:01<00:10, 4.20it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.20it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.20it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.21it/s]\n 24%|██▍ | 12/50 [00:02<00:09, 4.21it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.21it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.21it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.20it/s]\n 32%|███▏ | 16/50 [00:03<00:08, 4.20it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.20it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.20it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.20it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.20it/s]\n 42%|████▏ | 21/50 [00:05<00:06, 4.20it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.20it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.20it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.20it/s]\n 50%|█████ | 25/50 [00:05<00:05, 4.20it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.20it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.20it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.20it/s]\n 58%|█████▊ | 29/50 [00:06<00:05, 4.20it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.20it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.20it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.19it/s]\n 66%|██████▌ | 33/50 [00:07<00:04, 4.19it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.20it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.19it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.19it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.19it/s]\n 76%|███████▌ | 38/50 [00:09<00:02, 4.19it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.19it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.19it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.19it/s]\n 84%|████████▍ | 42/50 [00:10<00:01, 4.19it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.20it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.21it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.21it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.21it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.21it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.21it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.21it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.21it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.19it/s]", "metrics": { "predict_time": 17.35293483, "total_time": 19.778689 }, "output": [ "https://replicate.delivery/pbxt/DwemC0v5H9SsG6aZKq7m00RjbiksfCW0e1ybpendeiBfMowwE/out-0.png" ], "started_at": "2024-06-28T08:36:50.073754Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/1vgww2bbm1rgp0cgbqysfxncxr", "cancel": "https://api.replicate.com/v1/predictions/1vgww2bbm1rgp0cgbqysfxncxr/cancel" }, "version": "9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c" }Generated inUsing seed: 7336 Ensuring enough disk space... Free disk space: 1791625609216 Downloading weights: https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar 2024-06-28T08:36:50Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2e43e1cc9cefbe1d url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar 2024-06-28T08:36:51Z | INFO | [ Complete ] dest=/src/weights-cache/2e43e1cc9cefbe1d size="186 MB" total_elapsed=1.159s url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar b'' Downloaded weights in 1.3218357563018799 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: whiteclaws cans in football ground txt2img mode 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▏ | 1/50 [00:00<00:13, 3.68it/s] 4%|▍ | 2/50 [00:00<00:12, 3.96it/s] 6%|▌ | 3/50 [00:00<00:11, 4.06it/s] 8%|▊ | 4/50 [00:00<00:11, 4.12it/s] 10%|█ | 5/50 [00:01<00:10, 4.16it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.18it/s] 14%|█▍ | 7/50 [00:01<00:10, 4.19it/s] 16%|█▌ | 8/50 [00:01<00:10, 4.20it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.20it/s] 20%|██ | 10/50 [00:02<00:09, 4.20it/s] 22%|██▏ | 11/50 [00:02<00:09, 4.21it/s] 24%|██▍ | 12/50 [00:02<00:09, 4.21it/s] 26%|██▌ | 13/50 [00:03<00:08, 4.21it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.21it/s] 30%|███ | 15/50 [00:03<00:08, 4.20it/s] 32%|███▏ | 16/50 [00:03<00:08, 4.20it/s] 34%|███▍ | 17/50 [00:04<00:07, 4.20it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.20it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.20it/s] 40%|████ | 20/50 [00:04<00:07, 4.20it/s] 42%|████▏ | 21/50 [00:05<00:06, 4.20it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.20it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.20it/s] 48%|████▊ | 24/50 [00:05<00:06, 4.20it/s] 50%|█████ | 25/50 [00:05<00:05, 4.20it/s] 52%|█████▏ | 26/50 [00:06<00:05, 4.20it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.20it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.20it/s] 58%|█████▊ | 29/50 [00:06<00:05, 4.20it/s] 60%|██████ | 30/50 [00:07<00:04, 4.20it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.20it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.19it/s] 66%|██████▌ | 33/50 [00:07<00:04, 4.19it/s] 68%|██████▊ | 34/50 [00:08<00:03, 4.20it/s] 70%|███████ | 35/50 [00:08<00:03, 4.19it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.19it/s] 74%|███████▍ | 37/50 [00:08<00:03, 4.19it/s] 76%|███████▌ | 38/50 [00:09<00:02, 4.19it/s] 78%|███████▊ | 39/50 [00:09<00:02, 4.19it/s] 80%|████████ | 40/50 [00:09<00:02, 4.19it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.19it/s] 84%|████████▍ | 42/50 [00:10<00:01, 4.19it/s] 86%|████████▌ | 43/50 [00:10<00:01, 4.20it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.21it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.21it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.21it/s] 94%|█████████▍| 47/50 [00:11<00:00, 4.21it/s] 96%|█████████▌| 48/50 [00:11<00:00, 4.21it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.21it/s] 100%|██████████| 50/50 [00:11<00:00, 4.21it/s] 100%|██████████| 50/50 [00:11<00:00, 4.19it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681cIDbxra1hpnpdrgm0cgbqzaseyz18StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- whiteclaw can with kpop artist in football setting
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "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 }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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", { input: { width: 1024, height: 1024, prompt: "whiteclaw can with kpop artist in football setting", 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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", input={ "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "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.
Output
{ "completed_at": "2024-06-28T08:39:59.650679Z", "created_at": "2024-06-28T08:38:20.339000Z", "data_removed": false, "error": null, "id": "bxra1hpnpdrgm0cgbqzaseyz18", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "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 }, "logs": "Using seed: 21184\nEnsuring enough disk space...\nFree disk space: 2109885227008\nDownloading weights: https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\n2024-06-28T08:39:43Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2e43e1cc9cefbe1d url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\n2024-06-28T08:39:44Z | INFO | [ Complete ] dest=/src/weights-cache/2e43e1cc9cefbe1d size=\"186 MB\" total_elapsed=1.210s url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\nb''\nDownloaded weights in 1.2817060947418213 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: whiteclaw can with kpop artist in football setting\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)\nreturn F.conv2d(input, weight, bias, self.stride,\n/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▏ | 1/50 [00:00<00:20, 2.36it/s]\n 4%|▍ | 2/50 [00:00<00:14, 3.22it/s]\n 6%|▌ | 3/50 [00:00<00:12, 3.64it/s]\n 8%|▊ | 4/50 [00:01<00:11, 3.88it/s]\n 10%|█ | 5/50 [00:01<00:11, 4.02it/s]\n 12%|█▏ | 6/50 [00:01<00:10, 4.11it/s]\n 14%|█▍ | 7/50 [00:01<00:10, 4.17it/s]\n 16%|█▌ | 8/50 [00:02<00:09, 4.22it/s]\n 18%|█▊ | 9/50 [00:02<00:09, 4.24it/s]\n 20%|██ | 10/50 [00:02<00:09, 4.26it/s]\n 22%|██▏ | 11/50 [00:02<00:09, 4.27it/s]\n 24%|██▍ | 12/50 [00:02<00:08, 4.28it/s]\n 26%|██▌ | 13/50 [00:03<00:08, 4.28it/s]\n 28%|██▊ | 14/50 [00:03<00:08, 4.28it/s]\n 30%|███ | 15/50 [00:03<00:08, 4.28it/s]\n 32%|███▏ | 16/50 [00:03<00:07, 4.28it/s]\n 34%|███▍ | 17/50 [00:04<00:07, 4.28it/s]\n 36%|███▌ | 18/50 [00:04<00:07, 4.28it/s]\n 38%|███▊ | 19/50 [00:04<00:07, 4.27it/s]\n 40%|████ | 20/50 [00:04<00:07, 4.28it/s]\n 42%|████▏ | 21/50 [00:05<00:06, 4.28it/s]\n 44%|████▍ | 22/50 [00:05<00:06, 4.28it/s]\n 46%|████▌ | 23/50 [00:05<00:06, 4.28it/s]\n 48%|████▊ | 24/50 [00:05<00:06, 4.28it/s]\n 50%|█████ | 25/50 [00:06<00:05, 4.27it/s]\n 52%|█████▏ | 26/50 [00:06<00:05, 4.27it/s]\n 54%|█████▍ | 27/50 [00:06<00:05, 4.27it/s]\n 56%|█████▌ | 28/50 [00:06<00:05, 4.27it/s]\n 58%|█████▊ | 29/50 [00:06<00:04, 4.27it/s]\n 60%|██████ | 30/50 [00:07<00:04, 4.27it/s]\n 62%|██████▏ | 31/50 [00:07<00:04, 4.27it/s]\n 64%|██████▍ | 32/50 [00:07<00:04, 4.28it/s]\n 66%|██████▌ | 33/50 [00:07<00:03, 4.27it/s]\n 68%|██████▊ | 34/50 [00:08<00:03, 4.28it/s]\n 70%|███████ | 35/50 [00:08<00:03, 4.27it/s]\n 72%|███████▏ | 36/50 [00:08<00:03, 4.27it/s]\n 74%|███████▍ | 37/50 [00:08<00:03, 4.27it/s]\n 76%|███████▌ | 38/50 [00:09<00:02, 4.27it/s]\n 78%|███████▊ | 39/50 [00:09<00:02, 4.27it/s]\n 80%|████████ | 40/50 [00:09<00:02, 4.27it/s]\n 82%|████████▏ | 41/50 [00:09<00:02, 4.27it/s]\n 84%|████████▍ | 42/50 [00:09<00:01, 4.27it/s]\n 86%|████████▌ | 43/50 [00:10<00:01, 4.27it/s]\n 88%|████████▊ | 44/50 [00:10<00:01, 4.26it/s]\n 90%|█████████ | 45/50 [00:10<00:01, 4.26it/s]\n 92%|█████████▏| 46/50 [00:10<00:00, 4.26it/s]\n 94%|█████████▍| 47/50 [00:11<00:00, 4.26it/s]\n 96%|█████████▌| 48/50 [00:11<00:00, 4.26it/s]\n 98%|█████████▊| 49/50 [00:11<00:00, 4.26it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.26it/s]\n100%|██████████| 50/50 [00:11<00:00, 4.21it/s]", "metrics": { "predict_time": 16.030235871, "total_time": 99.311679 }, "output": [ "https://replicate.delivery/pbxt/DIOFfKTijzxjSSyhBqNUiuH9WOaldW0M8yEC6vjmcZtvRhhJA/out-0.png" ], "started_at": "2024-06-28T08:39:43.620443Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/bxra1hpnpdrgm0cgbqzaseyz18", "cancel": "https://api.replicate.com/v1/predictions/bxra1hpnpdrgm0cgbqzaseyz18/cancel" }, "version": "9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c" }Generated inUsing seed: 21184 Ensuring enough disk space... Free disk space: 2109885227008 Downloading weights: https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar 2024-06-28T08:39:43Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2e43e1cc9cefbe1d url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar 2024-06-28T08:39:44Z | INFO | [ Complete ] dest=/src/weights-cache/2e43e1cc9cefbe1d size="186 MB" total_elapsed=1.210s url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar b'' Downloaded weights in 1.2817060947418213 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: whiteclaw can with kpop artist in football setting txt2img mode 0%| | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.) return F.conv2d(input, weight, bias, self.stride, /usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▏ | 1/50 [00:00<00:20, 2.36it/s] 4%|▍ | 2/50 [00:00<00:14, 3.22it/s] 6%|▌ | 3/50 [00:00<00:12, 3.64it/s] 8%|▊ | 4/50 [00:01<00:11, 3.88it/s] 10%|█ | 5/50 [00:01<00:11, 4.02it/s] 12%|█▏ | 6/50 [00:01<00:10, 4.11it/s] 14%|█▍ | 7/50 [00:01<00:10, 4.17it/s] 16%|█▌ | 8/50 [00:02<00:09, 4.22it/s] 18%|█▊ | 9/50 [00:02<00:09, 4.24it/s] 20%|██ | 10/50 [00:02<00:09, 4.26it/s] 22%|██▏ | 11/50 [00:02<00:09, 4.27it/s] 24%|██▍ | 12/50 [00:02<00:08, 4.28it/s] 26%|██▌ | 13/50 [00:03<00:08, 4.28it/s] 28%|██▊ | 14/50 [00:03<00:08, 4.28it/s] 30%|███ | 15/50 [00:03<00:08, 4.28it/s] 32%|███▏ | 16/50 [00:03<00:07, 4.28it/s] 34%|███▍ | 17/50 [00:04<00:07, 4.28it/s] 36%|███▌ | 18/50 [00:04<00:07, 4.28it/s] 38%|███▊ | 19/50 [00:04<00:07, 4.27it/s] 40%|████ | 20/50 [00:04<00:07, 4.28it/s] 42%|████▏ | 21/50 [00:05<00:06, 4.28it/s] 44%|████▍ | 22/50 [00:05<00:06, 4.28it/s] 46%|████▌ | 23/50 [00:05<00:06, 4.28it/s] 48%|████▊ | 24/50 [00:05<00:06, 4.28it/s] 50%|█████ | 25/50 [00:06<00:05, 4.27it/s] 52%|█████▏ | 26/50 [00:06<00:05, 4.27it/s] 54%|█████▍ | 27/50 [00:06<00:05, 4.27it/s] 56%|█████▌ | 28/50 [00:06<00:05, 4.27it/s] 58%|█████▊ | 29/50 [00:06<00:04, 4.27it/s] 60%|██████ | 30/50 [00:07<00:04, 4.27it/s] 62%|██████▏ | 31/50 [00:07<00:04, 4.27it/s] 64%|██████▍ | 32/50 [00:07<00:04, 4.28it/s] 66%|██████▌ | 33/50 [00:07<00:03, 4.27it/s] 68%|██████▊ | 34/50 [00:08<00:03, 4.28it/s] 70%|███████ | 35/50 [00:08<00:03, 4.27it/s] 72%|███████▏ | 36/50 [00:08<00:03, 4.27it/s] 74%|███████▍ | 37/50 [00:08<00:03, 4.27it/s] 76%|███████▌ | 38/50 [00:09<00:02, 4.27it/s] 78%|███████▊ | 39/50 [00:09<00:02, 4.27it/s] 80%|████████ | 40/50 [00:09<00:02, 4.27it/s] 82%|████████▏ | 41/50 [00:09<00:02, 4.27it/s] 84%|████████▍ | 42/50 [00:09<00:01, 4.27it/s] 86%|████████▌ | 43/50 [00:10<00:01, 4.27it/s] 88%|████████▊ | 44/50 [00:10<00:01, 4.26it/s] 90%|█████████ | 45/50 [00:10<00:01, 4.26it/s] 92%|█████████▏| 46/50 [00:10<00:00, 4.26it/s] 94%|█████████▍| 47/50 [00:11<00:00, 4.26it/s] 96%|█████████▌| 48/50 [00:11<00:00, 4.26it/s] 98%|█████████▊| 49/50 [00:11<00:00, 4.26it/s] 100%|██████████| 50/50 [00:11<00:00, 4.26it/s] 100%|██████████| 50/50 [00:11<00:00, 4.21it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681cIDxqh6wky8t1rgj0cgbr0vvjaahgStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- whiteclaw can with kpop artist in football setting
- 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
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "refine": "expert_ensemble_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 }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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", { input: { width: 1024, height: 1024, prompt: "whiteclaw can with kpop artist in football setting", refine: "expert_ensemble_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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", input={ "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "refine": "expert_ensemble_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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "refine": "expert_ensemble_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.
Output
{ "completed_at": "2024-06-28T08:41:58.553200Z", "created_at": "2024-06-28T08:41:33.648000Z", "data_removed": false, "error": null, "id": "xqh6wky8t1rgj0cgbr0vvjaahg", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "refine": "expert_ensemble_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 }, "logs": "Using seed: 54393\nEnsuring enough disk space...\nFree disk space: 2133102190592\nDownloading weights: https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\n2024-06-28T08:41:39Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2e43e1cc9cefbe1d url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\n2024-06-28T08:41:43Z | INFO | [ Complete ] dest=/src/weights-cache/2e43e1cc9cefbe1d size=\"186 MB\" total_elapsed=3.926s url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar\nb''\nDownloaded weights in 4.019713878631592 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: whiteclaw can with kpop artist in football setting\ntxt2img mode\n 0%| | 0/40 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)\nreturn F.conv2d(input, weight, bias, self.stride,\n/usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`\ndeprecate(\n 2%|▎ | 1/40 [00:00<00:16, 2.41it/s]\n 5%|▌ | 2/40 [00:00<00:11, 3.25it/s]\n 8%|▊ | 3/40 [00:00<00:10, 3.65it/s]\n 10%|█ | 4/40 [00:01<00:09, 3.87it/s]\n 12%|█▎ | 5/40 [00:01<00:08, 3.99it/s]\n 15%|█▌ | 6/40 [00:01<00:08, 4.07it/s]\n 18%|█▊ | 7/40 [00:01<00:07, 4.13it/s]\n 20%|██ | 8/40 [00:02<00:07, 4.16it/s]\n 22%|██▎ | 9/40 [00:02<00:07, 4.19it/s]\n 25%|██▌ | 10/40 [00:02<00:07, 4.20it/s]\n 28%|██▊ | 11/40 [00:02<00:06, 4.21it/s]\n 30%|███ | 12/40 [00:03<00:06, 4.22it/s]\n 32%|███▎ | 13/40 [00:03<00:06, 4.22it/s]\n 35%|███▌ | 14/40 [00:03<00:06, 4.23it/s]\n 38%|███▊ | 15/40 [00:03<00:05, 4.22it/s]\n 40%|████ | 16/40 [00:03<00:05, 4.23it/s]\n 42%|████▎ | 17/40 [00:04<00:05, 4.23it/s]\n 45%|████▌ | 18/40 [00:04<00:05, 4.23it/s]\n 48%|████▊ | 19/40 [00:04<00:04, 4.23it/s]\n 50%|█████ | 20/40 [00:04<00:04, 4.23it/s]\n 52%|█████▎ | 21/40 [00:05<00:04, 4.23it/s]\n 55%|█████▌ | 22/40 [00:05<00:04, 4.24it/s]\n 57%|█████▊ | 23/40 [00:05<00:04, 4.23it/s]\n 60%|██████ | 24/40 [00:05<00:03, 4.23it/s]\n 62%|██████▎ | 25/40 [00:06<00:03, 4.23it/s]\n 65%|██████▌ | 26/40 [00:06<00:03, 4.23it/s]\n 68%|██████▊ | 27/40 [00:06<00:03, 4.22it/s]\n 70%|███████ | 28/40 [00:06<00:02, 4.23it/s]\n 72%|███████▎ | 29/40 [00:07<00:02, 4.24it/s]\n 75%|███████▌ | 30/40 [00:07<00:02, 4.24it/s]\n 78%|███████▊ | 31/40 [00:07<00:02, 4.24it/s]\n 80%|████████ | 32/40 [00:07<00:01, 4.25it/s]\n 82%|████████▎ | 33/40 [00:07<00:01, 4.25it/s]\n 85%|████████▌ | 34/40 [00:08<00:01, 4.25it/s]\n 88%|████████▊ | 35/40 [00:08<00:01, 4.25it/s]\n 90%|█████████ | 36/40 [00:08<00:00, 4.25it/s]\n 92%|█████████▎| 37/40 [00:08<00:00, 4.25it/s]\n 95%|█████████▌| 38/40 [00:09<00:00, 4.25it/s]\n 98%|█████████▊| 39/40 [00:09<00:00, 4.25it/s]\n100%|██████████| 40/40 [00:09<00:00, 4.25it/s]\n100%|██████████| 40/40 [00:09<00:00, 4.16it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 3.91it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.08it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.15it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.17it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.18it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.20it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.20it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.20it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.20it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.21it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.18it/s]", "metrics": { "predict_time": 18.843549297, "total_time": 24.9052 }, "output": [ "https://replicate.delivery/pbxt/GrU3YtFGVhpXH5aWIfRkbU6cIYd9SfftoSe3ViWT2WyZVKMMB/out-0.png" ], "started_at": "2024-06-28T08:41:39.709651Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xqh6wky8t1rgj0cgbr0vvjaahg", "cancel": "https://api.replicate.com/v1/predictions/xqh6wky8t1rgj0cgbr0vvjaahg/cancel" }, "version": "9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c" }Generated inUsing seed: 54393 Ensuring enough disk space... Free disk space: 2133102190592 Downloading weights: https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar 2024-06-28T08:41:39Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2e43e1cc9cefbe1d url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar 2024-06-28T08:41:43Z | INFO | [ Complete ] dest=/src/weights-cache/2e43e1cc9cefbe1d size="186 MB" total_elapsed=3.926s url=https://replicate.delivery/pbxt/yuEZ8eKXFuUpKStc9IjJidLgMdH3GIfVSund50NQ9WLGWCDTA/trained_model.tar b'' Downloaded weights in 4.019713878631592 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: whiteclaw can with kpop artist in football setting txt2img mode 0%| | 0/40 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.) return F.conv2d(input, weight, bias, self.stride, /usr/local/lib/python3.9/site-packages/diffusers/models/attention_processor.py:1946: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights` deprecate( 2%|▎ | 1/40 [00:00<00:16, 2.41it/s] 5%|▌ | 2/40 [00:00<00:11, 3.25it/s] 8%|▊ | 3/40 [00:00<00:10, 3.65it/s] 10%|█ | 4/40 [00:01<00:09, 3.87it/s] 12%|█▎ | 5/40 [00:01<00:08, 3.99it/s] 15%|█▌ | 6/40 [00:01<00:08, 4.07it/s] 18%|█▊ | 7/40 [00:01<00:07, 4.13it/s] 20%|██ | 8/40 [00:02<00:07, 4.16it/s] 22%|██▎ | 9/40 [00:02<00:07, 4.19it/s] 25%|██▌ | 10/40 [00:02<00:07, 4.20it/s] 28%|██▊ | 11/40 [00:02<00:06, 4.21it/s] 30%|███ | 12/40 [00:03<00:06, 4.22it/s] 32%|███▎ | 13/40 [00:03<00:06, 4.22it/s] 35%|███▌ | 14/40 [00:03<00:06, 4.23it/s] 38%|███▊ | 15/40 [00:03<00:05, 4.22it/s] 40%|████ | 16/40 [00:03<00:05, 4.23it/s] 42%|████▎ | 17/40 [00:04<00:05, 4.23it/s] 45%|████▌ | 18/40 [00:04<00:05, 4.23it/s] 48%|████▊ | 19/40 [00:04<00:04, 4.23it/s] 50%|█████ | 20/40 [00:04<00:04, 4.23it/s] 52%|█████▎ | 21/40 [00:05<00:04, 4.23it/s] 55%|█████▌ | 22/40 [00:05<00:04, 4.24it/s] 57%|█████▊ | 23/40 [00:05<00:04, 4.23it/s] 60%|██████ | 24/40 [00:05<00:03, 4.23it/s] 62%|██████▎ | 25/40 [00:06<00:03, 4.23it/s] 65%|██████▌ | 26/40 [00:06<00:03, 4.23it/s] 68%|██████▊ | 27/40 [00:06<00:03, 4.22it/s] 70%|███████ | 28/40 [00:06<00:02, 4.23it/s] 72%|███████▎ | 29/40 [00:07<00:02, 4.24it/s] 75%|███████▌ | 30/40 [00:07<00:02, 4.24it/s] 78%|███████▊ | 31/40 [00:07<00:02, 4.24it/s] 80%|████████ | 32/40 [00:07<00:01, 4.25it/s] 82%|████████▎ | 33/40 [00:07<00:01, 4.25it/s] 85%|████████▌ | 34/40 [00:08<00:01, 4.25it/s] 88%|████████▊ | 35/40 [00:08<00:01, 4.25it/s] 90%|█████████ | 36/40 [00:08<00:00, 4.25it/s] 92%|█████████▎| 37/40 [00:08<00:00, 4.25it/s] 95%|█████████▌| 38/40 [00:09<00:00, 4.25it/s] 98%|█████████▊| 39/40 [00:09<00:00, 4.25it/s] 100%|██████████| 40/40 [00:09<00:00, 4.25it/s] 100%|██████████| 40/40 [00:09<00:00, 4.16it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:02, 3.91it/s] 20%|██ | 2/10 [00:00<00:01, 4.08it/s] 30%|███ | 3/10 [00:00<00:01, 4.15it/s] 40%|████ | 4/10 [00:00<00:01, 4.17it/s] 50%|█████ | 5/10 [00:01<00:01, 4.18it/s] 60%|██████ | 6/10 [00:01<00:00, 4.20it/s] 70%|███████ | 7/10 [00:01<00:00, 4.20it/s] 80%|████████ | 8/10 [00:01<00:00, 4.20it/s] 90%|█████████ | 9/10 [00:02<00:00, 4.20it/s] 100%|██████████| 10/10 [00:02<00:00, 4.21it/s] 100%|██████████| 10/10 [00:02<00:00, 4.18it/s]Prediction
shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681cID421wna63r9rgm0cgbr29x993n4StatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- whiteclaw can with kpop artist in football setting
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.72
- num_outputs
- 4
- guidance_scale
- 15.9
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- blur faces of kpop artists
- prompt_strength
- 0.8
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 15.9, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "blur faces of kpop artists", "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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", { input: { width: 1024, height: 1024, prompt: "whiteclaw can with kpop artist in football setting", refine: "expert_ensemble_refiner", scheduler: "K_EULER", lora_scale: 0.72, num_outputs: 4, guidance_scale: 15.9, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "blur faces of kpop artists", 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 shahildhotre/sdxl-finetune-whiteclaw using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", input={ "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 15.9, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "blur faces of kpop artists", "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 shahildhotre/sdxl-finetune-whiteclaw 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": "shahildhotre/sdxl-finetune-whiteclaw:9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 15.9, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "blur faces of kpop artists", "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.
Output
{ "completed_at": "2024-06-28T08:45:45.785003Z", "created_at": "2024-06-28T08:44:48.962000Z", "data_removed": false, "error": null, "id": "421wna63r9rgm0cgbr29x993n4", "input": { "width": 1024, "height": 1024, "prompt": "whiteclaw can with kpop artist in football setting", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.72, "num_outputs": 4, "guidance_scale": 15.9, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "blur faces of kpop artists", "prompt_strength": 0.8, "num_inference_steps": 50 }, "logs": "Using seed: 38335\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: whiteclaw can with kpop artist in football setting\ntxt2img mode\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:00<00:35, 1.09it/s]\n 5%|▌ | 2/40 [00:01<00:34, 1.10it/s]\n 8%|▊ | 3/40 [00:02<00:33, 1.10it/s]\n 10%|█ | 4/40 [00:03<00:32, 1.10it/s]\n 12%|█▎ | 5/40 [00:04<00:31, 1.10it/s]\n 15%|█▌ | 6/40 [00:05<00:31, 1.10it/s]\n 18%|█▊ | 7/40 [00:06<00:30, 1.09it/s]\n 20%|██ | 8/40 [00:07<00:29, 1.09it/s]\n 22%|██▎ | 9/40 [00:08<00:28, 1.09it/s]\n 25%|██▌ | 10/40 [00:09<00:27, 1.09it/s]\n 28%|██▊ | 11/40 [00:10<00:26, 1.10it/s]\n 30%|███ | 12/40 [00:10<00:25, 1.10it/s]\n 32%|███▎ | 13/40 [00:11<00:24, 1.10it/s]\n 35%|███▌ | 14/40 [00:12<00:23, 1.10it/s]\n 38%|███▊ | 15/40 [00:13<00:22, 1.10it/s]\n 40%|████ | 16/40 [00:14<00:21, 1.10it/s]\n 42%|████▎ | 17/40 [00:15<00:20, 1.10it/s]\n 45%|████▌ | 18/40 [00:16<00:19, 1.10it/s]\n 48%|████▊ | 19/40 [00:17<00:19, 1.10it/s]\n 50%|█████ | 20/40 [00:18<00:18, 1.10it/s]\n 52%|█████▎ | 21/40 [00:19<00:17, 1.10it/s]\n 55%|█████▌ | 22/40 [00:20<00:16, 1.10it/s]\n 57%|█████▊ | 23/40 [00:20<00:15, 1.10it/s]\n 60%|██████ | 24/40 [00:21<00:14, 1.10it/s]\n 62%|██████▎ | 25/40 [00:22<00:13, 1.10it/s]\n 65%|██████▌ | 26/40 [00:23<00:12, 1.10it/s]\n 68%|██████▊ | 27/40 [00:24<00:11, 1.10it/s]\n 70%|███████ | 28/40 [00:25<00:10, 1.10it/s]\n 72%|███████▎ | 29/40 [00:26<00:10, 1.10it/s]\n 75%|███████▌ | 30/40 [00:27<00:09, 1.10it/s]\n 78%|███████▊ | 31/40 [00:28<00:08, 1.10it/s]\n 80%|████████ | 32/40 [00:29<00:07, 1.10it/s]\n 82%|████████▎ | 33/40 [00:30<00:06, 1.09it/s]\n 85%|████████▌ | 34/40 [00:30<00:05, 1.09it/s]\n 88%|████████▊ | 35/40 [00:31<00:04, 1.09it/s]\n 90%|█████████ | 36/40 [00:32<00:03, 1.09it/s]\n 92%|█████████▎| 37/40 [00:33<00:02, 1.09it/s]\n 95%|█████████▌| 38/40 [00:34<00:01, 1.09it/s]\n 98%|█████████▊| 39/40 [00:35<00:00, 1.09it/s]\n100%|██████████| 40/40 [00:36<00:00, 1.09it/s]\n100%|██████████| 40/40 [00:36<00:00, 1.10it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:08, 1.09it/s]\n 20%|██ | 2/10 [00:01<00:07, 1.09it/s]\n 30%|███ | 3/10 [00:02<00:06, 1.09it/s]\n 40%|████ | 4/10 [00:03<00:05, 1.09it/s]\n 50%|█████ | 5/10 [00:04<00:04, 1.10it/s]\n 60%|██████ | 6/10 [00:05<00:03, 1.10it/s]\n 70%|███████ | 7/10 [00:06<00:02, 1.10it/s]\n 80%|████████ | 8/10 [00:07<00:01, 1.10it/s]\n 90%|█████████ | 9/10 [00:08<00:00, 1.10it/s]\n100%|██████████| 10/10 [00:09<00:00, 1.10it/s]\n100%|██████████| 10/10 [00:09<00:00, 1.10it/s]", "metrics": { "predict_time": 54.296272399, "total_time": 56.823003 }, "output": [ "https://replicate.delivery/pbxt/xOfF5V2xJd1fhUa7jFB8bX7zA2gbRjZujUFGlHWsb914oCDTA/out-0.png", "https://replicate.delivery/pbxt/GRiqusNh3oLDBVies7H6w5uPHAz2ySOqKKUyosCOGY1cUhhJA/out-1.png", "https://replicate.delivery/pbxt/iSrz9pZQm9YwA9oDQbGIiJ7PeLQE9OKLf8qhsUWas8c5oCDTA/out-2.png", "https://replicate.delivery/pbxt/lwOTSPwWXe3PJSg4Jur1TQJ2XZt6CqMdUMNASQFC65rcUhhJA/out-3.png" ], "started_at": "2024-06-28T08:44:51.488731Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/421wna63r9rgm0cgbr29x993n4", "cancel": "https://api.replicate.com/v1/predictions/421wna63r9rgm0cgbr29x993n4/cancel" }, "version": "9dc225509e9572aed5dc6669cd9af17dc2b64db4d61899080c6ef1b27194681c" }Generated inUsing seed: 38335 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: whiteclaw can with kpop artist in football setting txt2img mode 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:00<00:35, 1.09it/s] 5%|▌ | 2/40 [00:01<00:34, 1.10it/s] 8%|▊ | 3/40 [00:02<00:33, 1.10it/s] 10%|█ | 4/40 [00:03<00:32, 1.10it/s] 12%|█▎ | 5/40 [00:04<00:31, 1.10it/s] 15%|█▌ | 6/40 [00:05<00:31, 1.10it/s] 18%|█▊ | 7/40 [00:06<00:30, 1.09it/s] 20%|██ | 8/40 [00:07<00:29, 1.09it/s] 22%|██▎ | 9/40 [00:08<00:28, 1.09it/s] 25%|██▌ | 10/40 [00:09<00:27, 1.09it/s] 28%|██▊ | 11/40 [00:10<00:26, 1.10it/s] 30%|███ | 12/40 [00:10<00:25, 1.10it/s] 32%|███▎ | 13/40 [00:11<00:24, 1.10it/s] 35%|███▌ | 14/40 [00:12<00:23, 1.10it/s] 38%|███▊ | 15/40 [00:13<00:22, 1.10it/s] 40%|████ | 16/40 [00:14<00:21, 1.10it/s] 42%|████▎ | 17/40 [00:15<00:20, 1.10it/s] 45%|████▌ | 18/40 [00:16<00:19, 1.10it/s] 48%|████▊ | 19/40 [00:17<00:19, 1.10it/s] 50%|█████ | 20/40 [00:18<00:18, 1.10it/s] 52%|█████▎ | 21/40 [00:19<00:17, 1.10it/s] 55%|█████▌ | 22/40 [00:20<00:16, 1.10it/s] 57%|█████▊ | 23/40 [00:20<00:15, 1.10it/s] 60%|██████ | 24/40 [00:21<00:14, 1.10it/s] 62%|██████▎ | 25/40 [00:22<00:13, 1.10it/s] 65%|██████▌ | 26/40 [00:23<00:12, 1.10it/s] 68%|██████▊ | 27/40 [00:24<00:11, 1.10it/s] 70%|███████ | 28/40 [00:25<00:10, 1.10it/s] 72%|███████▎ | 29/40 [00:26<00:10, 1.10it/s] 75%|███████▌ | 30/40 [00:27<00:09, 1.10it/s] 78%|███████▊ | 31/40 [00:28<00:08, 1.10it/s] 80%|████████ | 32/40 [00:29<00:07, 1.10it/s] 82%|████████▎ | 33/40 [00:30<00:06, 1.09it/s] 85%|████████▌ | 34/40 [00:30<00:05, 1.09it/s] 88%|████████▊ | 35/40 [00:31<00:04, 1.09it/s] 90%|█████████ | 36/40 [00:32<00:03, 1.09it/s] 92%|█████████▎| 37/40 [00:33<00:02, 1.09it/s] 95%|█████████▌| 38/40 [00:34<00:01, 1.09it/s] 98%|█████████▊| 39/40 [00:35<00:00, 1.09it/s] 100%|██████████| 40/40 [00:36<00:00, 1.09it/s] 100%|██████████| 40/40 [00:36<00:00, 1.10it/s] 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:08, 1.09it/s] 20%|██ | 2/10 [00:01<00:07, 1.09it/s] 30%|███ | 3/10 [00:02<00:06, 1.09it/s] 40%|████ | 4/10 [00:03<00:05, 1.09it/s] 50%|█████ | 5/10 [00:04<00:04, 1.10it/s] 60%|██████ | 6/10 [00:05<00:03, 1.10it/s] 70%|███████ | 7/10 [00:06<00:02, 1.10it/s] 80%|████████ | 8/10 [00:07<00:01, 1.10it/s] 90%|█████████ | 9/10 [00:08<00:00, 1.10it/s] 100%|██████████| 10/10 [00:09<00:00, 1.10it/s] 100%|██████████| 10/10 [00:09<00:00, 1.10it/s]
Want to make some of these yourself?
Run this model