hughjsmith / martine
A model trained on images of United Therapeutics CEO Dr. Martine Rothblatt (Updated 1 year, 6 months ago)
- Public
- 22 runs
- SDXL fine-tune
Prediction
hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5ccIDje5vihlbamjnzajejsrwmvc7vuStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- Show me an image of Martine in front of a rainbow
- refine
- no_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 1
- guidance_scale
- 10.75
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.85
- num_inference_steps
- 67
{ "width": 1024, "height": 1024, "prompt": "Show me an image of Martine in front of a rainbow", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.85, "num_inference_steps": 67 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run hughjsmith/martine using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", { input: { width: 1024, height: 1024, prompt: "Show me an image of Martine in front of a rainbow", refine: "no_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 1, guidance_scale: 10.75, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", prompt_strength: 0.85, num_inference_steps: 67 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run hughjsmith/martine using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", input={ "width": 1024, "height": 1024, "prompt": "Show me an image of Martine in front of a rainbow", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10.75, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.85, "num_inference_steps": 67 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run hughjsmith/martine 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": "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", "input": { "width": 1024, "height": 1024, "prompt": "Show me an image of Martine in front of a rainbow", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.85, "num_inference_steps": 67 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-02T20:16:06.941543Z", "created_at": "2024-01-02T20:15:19.599683Z", "data_removed": false, "error": null, "id": "je5vihlbamjnzajejsrwmvc7vu", "input": { "width": 1024, "height": 1024, "prompt": "Show me an image of Martine in front of a rainbow", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.85, "num_inference_steps": 67 }, "logs": "Using seed: 3357\nEnsuring enough disk space...\nFree disk space: 1566356209664\nDownloading weights: https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar\n2024-01-02T20:15:37Z | INFO | [ Initiating ] dest=/src/weights-cache/d7925bd432f7746b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar\n2024-01-02T20:15:46Z | INFO | [ Complete ] dest=/src/weights-cache/d7925bd432f7746b size=\"186 MB\" total_elapsed=8.843s url=https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar\nb''\nDownloaded weights in 9.062646389007568 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: Show me an image of Martine in front of a rainbow\ntxt2img mode\n 0%| | 0/67 [00:00<?, ?it/s]\n 1%|▏ | 1/67 [00:00<00:17, 3.69it/s]\n 3%|▎ | 2/67 [00:00<00:17, 3.67it/s]\n 4%|▍ | 3/67 [00:00<00:17, 3.66it/s]\n 6%|▌ | 4/67 [00:01<00:17, 3.66it/s]\n 7%|▋ | 5/67 [00:01<00:16, 3.66it/s]\n 9%|▉ | 6/67 [00:01<00:16, 3.65it/s]\n 10%|█ | 7/67 [00:01<00:16, 3.65it/s]\n 12%|█▏ | 8/67 [00:02<00:16, 3.65it/s]\n 13%|█▎ | 9/67 [00:02<00:15, 3.65it/s]\n 15%|█▍ | 10/67 [00:02<00:15, 3.65it/s]\n 16%|█▋ | 11/67 [00:03<00:15, 3.66it/s]\n 18%|█▊ | 12/67 [00:03<00:15, 3.66it/s]\n 19%|█▉ | 13/67 [00:03<00:14, 3.66it/s]\n 21%|██ | 14/67 [00:03<00:14, 3.66it/s]\n 22%|██▏ | 15/67 [00:04<00:14, 3.66it/s]\n 24%|██▍ | 16/67 [00:04<00:13, 3.67it/s]\n 25%|██▌ | 17/67 [00:04<00:13, 3.67it/s]\n 27%|██▋ | 18/67 [00:04<00:13, 3.67it/s]\n 28%|██▊ | 19/67 [00:05<00:13, 3.67it/s]\n 30%|██▉ | 20/67 [00:05<00:12, 3.67it/s]\n 31%|███▏ | 21/67 [00:05<00:12, 3.67it/s]\n 33%|███▎ | 22/67 [00:06<00:12, 3.67it/s]\n 34%|███▍ | 23/67 [00:06<00:11, 3.67it/s]\n 36%|███▌ | 24/67 [00:06<00:11, 3.67it/s]\n 37%|███▋ | 25/67 [00:06<00:11, 3.66it/s]\n 39%|███▉ | 26/67 [00:07<00:11, 3.67it/s]\n 40%|████ | 27/67 [00:07<00:10, 3.67it/s]\n 42%|████▏ | 28/67 [00:07<00:10, 3.67it/s]\n 43%|████▎ | 29/67 [00:07<00:10, 3.66it/s]\n 45%|████▍ | 30/67 [00:08<00:10, 3.66it/s]\n 46%|████▋ | 31/67 [00:08<00:09, 3.66it/s]\n 48%|████▊ | 32/67 [00:08<00:09, 3.66it/s]\n 49%|████▉ | 33/67 [00:09<00:09, 3.66it/s]\n 51%|█████ | 34/67 [00:09<00:09, 3.66it/s]\n 52%|█████▏ | 35/67 [00:09<00:08, 3.66it/s]\n 54%|█████▎ | 36/67 [00:09<00:08, 3.65it/s]\n 55%|█████▌ | 37/67 [00:10<00:08, 3.66it/s]\n 57%|█████▋ | 38/67 [00:10<00:07, 3.65it/s]\n 58%|█████▊ | 39/67 [00:10<00:07, 3.65it/s]\n 60%|█████▉ | 40/67 [00:10<00:07, 3.65it/s]\n 61%|██████ | 41/67 [00:11<00:07, 3.65it/s]\n 63%|██████▎ | 42/67 [00:11<00:06, 3.65it/s]\n 64%|██████▍ | 43/67 [00:11<00:06, 3.66it/s]\n 66%|██████▌ | 44/67 [00:12<00:06, 3.66it/s]\n 67%|██████▋ | 45/67 [00:12<00:06, 3.66it/s]\n 69%|██████▊ | 46/67 [00:12<00:05, 3.66it/s]\n 70%|███████ | 47/67 [00:12<00:05, 3.66it/s]\n 72%|███████▏ | 48/67 [00:13<00:05, 3.65it/s]\n 73%|███████▎ | 49/67 [00:13<00:04, 3.65it/s]\n 75%|███████▍ | 50/67 [00:13<00:04, 3.65it/s]\n 76%|███████▌ | 51/67 [00:13<00:04, 3.65it/s]\n 78%|███████▊ | 52/67 [00:14<00:04, 3.65it/s]\n 79%|███████▉ | 53/67 [00:14<00:03, 3.65it/s]\n 81%|████████ | 54/67 [00:14<00:03, 3.65it/s]\n 82%|████████▏ | 55/67 [00:15<00:03, 3.62it/s]\n 84%|████████▎ | 56/67 [00:15<00:03, 3.61it/s]\n 85%|████████▌ | 57/67 [00:15<00:02, 3.62it/s]\n 87%|████████▋ | 58/67 [00:15<00:02, 3.63it/s]\n 88%|████████▊ | 59/67 [00:16<00:02, 3.63it/s]\n 90%|████████▉ | 60/67 [00:16<00:01, 3.64it/s]\n 91%|█████████ | 61/67 [00:16<00:01, 3.64it/s]\n 93%|█████████▎| 62/67 [00:16<00:01, 3.64it/s]\n 94%|█████████▍| 63/67 [00:17<00:01, 3.64it/s]\n 96%|█████████▌| 64/67 [00:17<00:00, 3.64it/s]\n 97%|█████████▋| 65/67 [00:17<00:00, 3.65it/s]\n 99%|█████████▊| 66/67 [00:18<00:00, 3.64it/s]\n100%|██████████| 67/67 [00:18<00:00, 3.64it/s]\n100%|██████████| 67/67 [00:18<00:00, 3.65it/s]", "metrics": { "predict_time": 29.407761, "total_time": 47.34186 }, "output": [ "https://replicate.delivery/pbxt/btkbsGQcTHYEPZt79ctYuQbwTy1eWxTtOk2bTwJ0oDWDCREJA/out-0.png" ], "started_at": "2024-01-02T20:15:37.533782Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/je5vihlbamjnzajejsrwmvc7vu", "cancel": "https://api.replicate.com/v1/predictions/je5vihlbamjnzajejsrwmvc7vu/cancel" }, "version": "6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc" }
Generated inUsing seed: 3357 Ensuring enough disk space... Free disk space: 1566356209664 Downloading weights: https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar 2024-01-02T20:15:37Z | INFO | [ Initiating ] dest=/src/weights-cache/d7925bd432f7746b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar 2024-01-02T20:15:46Z | INFO | [ Complete ] dest=/src/weights-cache/d7925bd432f7746b size="186 MB" total_elapsed=8.843s url=https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar b'' Downloaded weights in 9.062646389007568 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: Show me an image of Martine in front of a rainbow txt2img mode 0%| | 0/67 [00:00<?, ?it/s] 1%|▏ | 1/67 [00:00<00:17, 3.69it/s] 3%|▎ | 2/67 [00:00<00:17, 3.67it/s] 4%|▍ | 3/67 [00:00<00:17, 3.66it/s] 6%|▌ | 4/67 [00:01<00:17, 3.66it/s] 7%|▋ | 5/67 [00:01<00:16, 3.66it/s] 9%|▉ | 6/67 [00:01<00:16, 3.65it/s] 10%|█ | 7/67 [00:01<00:16, 3.65it/s] 12%|█▏ | 8/67 [00:02<00:16, 3.65it/s] 13%|█▎ | 9/67 [00:02<00:15, 3.65it/s] 15%|█▍ | 10/67 [00:02<00:15, 3.65it/s] 16%|█▋ | 11/67 [00:03<00:15, 3.66it/s] 18%|█▊ | 12/67 [00:03<00:15, 3.66it/s] 19%|█▉ | 13/67 [00:03<00:14, 3.66it/s] 21%|██ | 14/67 [00:03<00:14, 3.66it/s] 22%|██▏ | 15/67 [00:04<00:14, 3.66it/s] 24%|██▍ | 16/67 [00:04<00:13, 3.67it/s] 25%|██▌ | 17/67 [00:04<00:13, 3.67it/s] 27%|██▋ | 18/67 [00:04<00:13, 3.67it/s] 28%|██▊ | 19/67 [00:05<00:13, 3.67it/s] 30%|██▉ | 20/67 [00:05<00:12, 3.67it/s] 31%|███▏ | 21/67 [00:05<00:12, 3.67it/s] 33%|███▎ | 22/67 [00:06<00:12, 3.67it/s] 34%|███▍ | 23/67 [00:06<00:11, 3.67it/s] 36%|███▌ | 24/67 [00:06<00:11, 3.67it/s] 37%|███▋ | 25/67 [00:06<00:11, 3.66it/s] 39%|███▉ | 26/67 [00:07<00:11, 3.67it/s] 40%|████ | 27/67 [00:07<00:10, 3.67it/s] 42%|████▏ | 28/67 [00:07<00:10, 3.67it/s] 43%|████▎ | 29/67 [00:07<00:10, 3.66it/s] 45%|████▍ | 30/67 [00:08<00:10, 3.66it/s] 46%|████▋ | 31/67 [00:08<00:09, 3.66it/s] 48%|████▊ | 32/67 [00:08<00:09, 3.66it/s] 49%|████▉ | 33/67 [00:09<00:09, 3.66it/s] 51%|█████ | 34/67 [00:09<00:09, 3.66it/s] 52%|█████▏ | 35/67 [00:09<00:08, 3.66it/s] 54%|█████▎ | 36/67 [00:09<00:08, 3.65it/s] 55%|█████▌ | 37/67 [00:10<00:08, 3.66it/s] 57%|█████▋ | 38/67 [00:10<00:07, 3.65it/s] 58%|█████▊ | 39/67 [00:10<00:07, 3.65it/s] 60%|█████▉ | 40/67 [00:10<00:07, 3.65it/s] 61%|██████ | 41/67 [00:11<00:07, 3.65it/s] 63%|██████▎ | 42/67 [00:11<00:06, 3.65it/s] 64%|██████▍ | 43/67 [00:11<00:06, 3.66it/s] 66%|██████▌ | 44/67 [00:12<00:06, 3.66it/s] 67%|██████▋ | 45/67 [00:12<00:06, 3.66it/s] 69%|██████▊ | 46/67 [00:12<00:05, 3.66it/s] 70%|███████ | 47/67 [00:12<00:05, 3.66it/s] 72%|███████▏ | 48/67 [00:13<00:05, 3.65it/s] 73%|███████▎ | 49/67 [00:13<00:04, 3.65it/s] 75%|███████▍ | 50/67 [00:13<00:04, 3.65it/s] 76%|███████▌ | 51/67 [00:13<00:04, 3.65it/s] 78%|███████▊ | 52/67 [00:14<00:04, 3.65it/s] 79%|███████▉ | 53/67 [00:14<00:03, 3.65it/s] 81%|████████ | 54/67 [00:14<00:03, 3.65it/s] 82%|████████▏ | 55/67 [00:15<00:03, 3.62it/s] 84%|████████▎ | 56/67 [00:15<00:03, 3.61it/s] 85%|████████▌ | 57/67 [00:15<00:02, 3.62it/s] 87%|████████▋ | 58/67 [00:15<00:02, 3.63it/s] 88%|████████▊ | 59/67 [00:16<00:02, 3.63it/s] 90%|████████▉ | 60/67 [00:16<00:01, 3.64it/s] 91%|█████████ | 61/67 [00:16<00:01, 3.64it/s] 93%|█████████▎| 62/67 [00:16<00:01, 3.64it/s] 94%|█████████▍| 63/67 [00:17<00:01, 3.64it/s] 96%|█████████▌| 64/67 [00:17<00:00, 3.64it/s] 97%|█████████▋| 65/67 [00:17<00:00, 3.65it/s] 99%|█████████▊| 66/67 [00:18<00:00, 3.64it/s] 100%|██████████| 67/67 [00:18<00:00, 3.64it/s] 100%|██████████| 67/67 [00:18<00:00, 3.65it/s]
Prediction
hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5ccIDlpeq353bj4tvpxlvgy2drlfqyqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 0
- width
- 1024
- height
- 1024
- prompt
- Show me a photorealistic image of Martine in front of a rainbow
- refine
- base_image_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 3
- guidance_scale
- 10.75
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.69
- num_inference_steps
- 78
{ "seed": 0, "width": 1024, "height": 1024, "prompt": "Show me a photorealistic image of Martine in front of a rainbow", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 3, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 78 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run hughjsmith/martine using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", { input: { seed: 0, width: 1024, height: 1024, prompt: "Show me a photorealistic image of Martine in front of a rainbow", refine: "base_image_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 3, guidance_scale: 10.75, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", prompt_strength: 0.69, num_inference_steps: 78 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run hughjsmith/martine using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", input={ "seed": 0, "width": 1024, "height": 1024, "prompt": "Show me a photorealistic image of Martine in front of a rainbow", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 3, "guidance_scale": 10.75, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 78 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run hughjsmith/martine 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": "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", "input": { "seed": 0, "width": 1024, "height": 1024, "prompt": "Show me a photorealistic image of Martine in front of a rainbow", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 3, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 78 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-28T01:29:46.584859Z", "created_at": "2024-01-28T01:28:14.126529Z", "data_removed": false, "error": null, "id": "lpeq353bj4tvpxlvgy2drlfqyq", "input": { "seed": 0, "width": 1024, "height": 1024, "prompt": "Show me a photorealistic image of Martine in front of a rainbow", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 3, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 78 }, "logs": "Using seed: 0\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: Show me a photorealistic image of Martine in front of a rainbow\ntxt2img mode\n 0%| | 0/78 [00:00<?, ?it/s]\n 1%|▏ | 1/78 [00:00<00:59, 1.28it/s]\n 3%|▎ | 2/78 [00:01<00:59, 1.28it/s]\n 4%|▍ | 3/78 [00:02<00:58, 1.28it/s]\n 5%|▌ | 4/78 [00:03<00:57, 1.28it/s]\n 6%|▋ | 5/78 [00:03<00:56, 1.28it/s]\n 8%|▊ | 6/78 [00:04<00:56, 1.28it/s]\n 9%|▉ | 7/78 [00:05<00:55, 1.28it/s]\n 10%|█ | 8/78 [00:06<00:54, 1.28it/s]\n 12%|█▏ | 9/78 [00:07<00:54, 1.28it/s]\n 13%|█▎ | 10/78 [00:07<00:53, 1.28it/s]\n 14%|█▍ | 11/78 [00:08<00:52, 1.28it/s]\n 15%|█▌ | 12/78 [00:09<00:51, 1.28it/s]\n 17%|█▋ | 13/78 [00:10<00:50, 1.28it/s]\n 18%|█▊ | 14/78 [00:10<00:50, 1.28it/s]\n 19%|█▉ | 15/78 [00:11<00:49, 1.28it/s]\n 21%|██ | 16/78 [00:12<00:48, 1.28it/s]\n 22%|██▏ | 17/78 [00:13<00:47, 1.28it/s]\n 23%|██▎ | 18/78 [00:14<00:47, 1.28it/s]\n 24%|██▍ | 19/78 [00:14<00:46, 1.28it/s]\n 26%|██▌ | 20/78 [00:15<00:45, 1.28it/s]\n 27%|██▋ | 21/78 [00:16<00:44, 1.28it/s]\n 28%|██▊ | 22/78 [00:17<00:43, 1.27it/s]\n 29%|██▉ | 23/78 [00:18<00:43, 1.28it/s]\n 31%|███ | 24/78 [00:18<00:42, 1.28it/s]\n 32%|███▏ | 25/78 [00:19<00:41, 1.27it/s]\n 33%|███▎ | 26/78 [00:20<00:40, 1.27it/s]\n 35%|███▍ | 27/78 [00:21<00:40, 1.27it/s]\n 36%|███▌ | 28/78 [00:21<00:39, 1.27it/s]\n 37%|███▋ | 29/78 [00:22<00:38, 1.27it/s]\n 38%|███▊ | 30/78 [00:23<00:37, 1.27it/s]\n 40%|███▉ | 31/78 [00:24<00:36, 1.27it/s]\n 41%|████ | 32/78 [00:25<00:36, 1.27it/s]\n 42%|████▏ | 33/78 [00:25<00:35, 1.27it/s]\n 44%|████▎ | 34/78 [00:26<00:34, 1.27it/s]\n 45%|████▍ | 35/78 [00:27<00:33, 1.27it/s]\n 46%|████▌ | 36/78 [00:28<00:32, 1.27it/s]\n 47%|████▋ | 37/78 [00:29<00:32, 1.27it/s]\n 49%|████▊ | 38/78 [00:29<00:31, 1.27it/s]\n 50%|█████ | 39/78 [00:30<00:30, 1.27it/s]\n 51%|█████▏ | 40/78 [00:31<00:29, 1.28it/s]\n 53%|█████▎ | 41/78 [00:32<00:29, 1.27it/s]\n 54%|█████▍ | 42/78 [00:32<00:28, 1.27it/s]\n 55%|█████▌ | 43/78 [00:33<00:27, 1.27it/s]\n 56%|█████▋ | 44/78 [00:34<00:26, 1.27it/s]\n 58%|█████▊ | 45/78 [00:35<00:25, 1.28it/s]\n 59%|█████▉ | 46/78 [00:36<00:25, 1.27it/s]\n 60%|██████ | 47/78 [00:36<00:24, 1.27it/s]\n 62%|██████▏ | 48/78 [00:37<00:23, 1.27it/s]\n 63%|██████▎ | 49/78 [00:38<00:22, 1.27it/s]\n 64%|██████▍ | 50/78 [00:39<00:22, 1.27it/s]\n 65%|██████▌ | 51/78 [00:39<00:21, 1.27it/s]\n 67%|██████▋ | 52/78 [00:40<00:20, 1.27it/s]\n 68%|██████▊ | 53/78 [00:41<00:19, 1.27it/s]\n 69%|██████▉ | 54/78 [00:42<00:18, 1.27it/s]\n 71%|███████ | 55/78 [00:43<00:18, 1.27it/s]\n 72%|███████▏ | 56/78 [00:43<00:17, 1.27it/s]\n 73%|███████▎ | 57/78 [00:44<00:16, 1.27it/s]\n 74%|███████▍ | 58/78 [00:45<00:15, 1.27it/s]\n 76%|███████▌ | 59/78 [00:46<00:14, 1.27it/s]\n 77%|███████▋ | 60/78 [00:47<00:14, 1.27it/s]\n 78%|███████▊ | 61/78 [00:47<00:13, 1.27it/s]\n 79%|███████▉ | 62/78 [00:48<00:12, 1.27it/s]\n 81%|████████ | 63/78 [00:49<00:11, 1.27it/s]\n 82%|████████▏ | 64/78 [00:50<00:10, 1.27it/s]\n 83%|████████▎ | 65/78 [00:50<00:10, 1.27it/s]\n 85%|████████▍ | 66/78 [00:51<00:09, 1.27it/s]\n 86%|████████▌ | 67/78 [00:52<00:08, 1.27it/s]\n 87%|████████▋ | 68/78 [00:53<00:07, 1.27it/s]\n 88%|████████▊ | 69/78 [00:54<00:07, 1.27it/s]\n 90%|████████▉ | 70/78 [00:54<00:06, 1.27it/s]\n 91%|█████████ | 71/78 [00:55<00:05, 1.27it/s]\n 92%|█████████▏| 72/78 [00:56<00:04, 1.27it/s]\n 94%|█████████▎| 73/78 [00:57<00:03, 1.27it/s]\n 95%|█████████▍| 74/78 [00:58<00:03, 1.27it/s]\n 96%|█████████▌| 75/78 [00:58<00:02, 1.27it/s]\n 97%|█████████▋| 76/78 [00:59<00:01, 1.27it/s]\n 99%|█████████▊| 77/78 [01:00<00:00, 1.27it/s]\n100%|██████████| 78/78 [01:01<00:00, 1.27it/s]\n100%|██████████| 78/78 [01:01<00:00, 1.27it/s]\n 0%| | 0/23 [00:00<?, ?it/s]\n 4%|▍ | 1/23 [00:00<00:14, 1.47it/s]\n 9%|▊ | 2/23 [00:01<00:14, 1.47it/s]\n 13%|█▎ | 3/23 [00:02<00:13, 1.48it/s]\n 17%|█▋ | 4/23 [00:02<00:12, 1.48it/s]\n 22%|██▏ | 5/23 [00:03<00:12, 1.48it/s]\n 26%|██▌ | 6/23 [00:04<00:11, 1.48it/s]\n 30%|███ | 7/23 [00:04<00:10, 1.48it/s]\n 35%|███▍ | 8/23 [00:05<00:10, 1.48it/s]\n 39%|███▉ | 9/23 [00:06<00:09, 1.48it/s]\n 43%|████▎ | 10/23 [00:06<00:08, 1.48it/s]\n 48%|████▊ | 11/23 [00:07<00:08, 1.48it/s]\n 52%|█████▏ | 12/23 [00:08<00:07, 1.48it/s]\n 57%|█████▋ | 13/23 [00:08<00:06, 1.48it/s]\n 61%|██████ | 14/23 [00:09<00:06, 1.48it/s]\n 65%|██████▌ | 15/23 [00:10<00:05, 1.48it/s]\n 70%|██████▉ | 16/23 [00:10<00:04, 1.48it/s]\n 74%|███████▍ | 17/23 [00:11<00:04, 1.48it/s]\n 78%|███████▊ | 18/23 [00:12<00:03, 1.48it/s]\n 83%|████████▎ | 19/23 [00:12<00:02, 1.48it/s]\n 87%|████████▋ | 20/23 [00:13<00:02, 1.48it/s]\n 91%|█████████▏| 21/23 [00:14<00:01, 1.48it/s]\n 96%|█████████▌| 22/23 [00:14<00:00, 1.48it/s]\n100%|██████████| 23/23 [00:15<00:00, 1.48it/s]\n100%|██████████| 23/23 [00:15<00:00, 1.48it/s]", "metrics": { "predict_time": 82.177495, "total_time": 92.45833 }, "output": [ "https://replicate.delivery/pbxt/i7WedFndhFwzKKLGo4TEs4qWwfppxSeh8eZigovtBLslAYDJB/out-0.png", "https://replicate.delivery/pbxt/XOgcE6isfd2aVyDNBOwFGGQFv11SBtTvwgGFIagevVEJA2QSA/out-1.png", "https://replicate.delivery/pbxt/UsXXVe1ANPUpbSNsW9T8auPVlfZLDFfSv8dYzfYc42cpAYDJB/out-2.png" ], "started_at": "2024-01-28T01:28:24.407364Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/lpeq353bj4tvpxlvgy2drlfqyq", "cancel": "https://api.replicate.com/v1/predictions/lpeq353bj4tvpxlvgy2drlfqyq/cancel" }, "version": "6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc" }
Generated inUsing seed: 0 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: Show me a photorealistic image of Martine in front of a rainbow txt2img mode 0%| | 0/78 [00:00<?, ?it/s] 1%|▏ | 1/78 [00:00<00:59, 1.28it/s] 3%|▎ | 2/78 [00:01<00:59, 1.28it/s] 4%|▍ | 3/78 [00:02<00:58, 1.28it/s] 5%|▌ | 4/78 [00:03<00:57, 1.28it/s] 6%|▋ | 5/78 [00:03<00:56, 1.28it/s] 8%|▊ | 6/78 [00:04<00:56, 1.28it/s] 9%|▉ | 7/78 [00:05<00:55, 1.28it/s] 10%|█ | 8/78 [00:06<00:54, 1.28it/s] 12%|█▏ | 9/78 [00:07<00:54, 1.28it/s] 13%|█▎ | 10/78 [00:07<00:53, 1.28it/s] 14%|█▍ | 11/78 [00:08<00:52, 1.28it/s] 15%|█▌ | 12/78 [00:09<00:51, 1.28it/s] 17%|█▋ | 13/78 [00:10<00:50, 1.28it/s] 18%|█▊ | 14/78 [00:10<00:50, 1.28it/s] 19%|█▉ | 15/78 [00:11<00:49, 1.28it/s] 21%|██ | 16/78 [00:12<00:48, 1.28it/s] 22%|██▏ | 17/78 [00:13<00:47, 1.28it/s] 23%|██▎ | 18/78 [00:14<00:47, 1.28it/s] 24%|██▍ | 19/78 [00:14<00:46, 1.28it/s] 26%|██▌ | 20/78 [00:15<00:45, 1.28it/s] 27%|██▋ | 21/78 [00:16<00:44, 1.28it/s] 28%|██▊ | 22/78 [00:17<00:43, 1.27it/s] 29%|██▉ | 23/78 [00:18<00:43, 1.28it/s] 31%|███ | 24/78 [00:18<00:42, 1.28it/s] 32%|███▏ | 25/78 [00:19<00:41, 1.27it/s] 33%|███▎ | 26/78 [00:20<00:40, 1.27it/s] 35%|███▍ | 27/78 [00:21<00:40, 1.27it/s] 36%|███▌ | 28/78 [00:21<00:39, 1.27it/s] 37%|███▋ | 29/78 [00:22<00:38, 1.27it/s] 38%|███▊ | 30/78 [00:23<00:37, 1.27it/s] 40%|███▉ | 31/78 [00:24<00:36, 1.27it/s] 41%|████ | 32/78 [00:25<00:36, 1.27it/s] 42%|████▏ | 33/78 [00:25<00:35, 1.27it/s] 44%|████▎ | 34/78 [00:26<00:34, 1.27it/s] 45%|████▍ | 35/78 [00:27<00:33, 1.27it/s] 46%|████▌ | 36/78 [00:28<00:32, 1.27it/s] 47%|████▋ | 37/78 [00:29<00:32, 1.27it/s] 49%|████▊ | 38/78 [00:29<00:31, 1.27it/s] 50%|█████ | 39/78 [00:30<00:30, 1.27it/s] 51%|█████▏ | 40/78 [00:31<00:29, 1.28it/s] 53%|█████▎ | 41/78 [00:32<00:29, 1.27it/s] 54%|█████▍ | 42/78 [00:32<00:28, 1.27it/s] 55%|█████▌ | 43/78 [00:33<00:27, 1.27it/s] 56%|█████▋ | 44/78 [00:34<00:26, 1.27it/s] 58%|█████▊ | 45/78 [00:35<00:25, 1.28it/s] 59%|█████▉ | 46/78 [00:36<00:25, 1.27it/s] 60%|██████ | 47/78 [00:36<00:24, 1.27it/s] 62%|██████▏ | 48/78 [00:37<00:23, 1.27it/s] 63%|██████▎ | 49/78 [00:38<00:22, 1.27it/s] 64%|██████▍ | 50/78 [00:39<00:22, 1.27it/s] 65%|██████▌ | 51/78 [00:39<00:21, 1.27it/s] 67%|██████▋ | 52/78 [00:40<00:20, 1.27it/s] 68%|██████▊ | 53/78 [00:41<00:19, 1.27it/s] 69%|██████▉ | 54/78 [00:42<00:18, 1.27it/s] 71%|███████ | 55/78 [00:43<00:18, 1.27it/s] 72%|███████▏ | 56/78 [00:43<00:17, 1.27it/s] 73%|███████▎ | 57/78 [00:44<00:16, 1.27it/s] 74%|███████▍ | 58/78 [00:45<00:15, 1.27it/s] 76%|███████▌ | 59/78 [00:46<00:14, 1.27it/s] 77%|███████▋ | 60/78 [00:47<00:14, 1.27it/s] 78%|███████▊ | 61/78 [00:47<00:13, 1.27it/s] 79%|███████▉ | 62/78 [00:48<00:12, 1.27it/s] 81%|████████ | 63/78 [00:49<00:11, 1.27it/s] 82%|████████▏ | 64/78 [00:50<00:10, 1.27it/s] 83%|████████▎ | 65/78 [00:50<00:10, 1.27it/s] 85%|████████▍ | 66/78 [00:51<00:09, 1.27it/s] 86%|████████▌ | 67/78 [00:52<00:08, 1.27it/s] 87%|████████▋ | 68/78 [00:53<00:07, 1.27it/s] 88%|████████▊ | 69/78 [00:54<00:07, 1.27it/s] 90%|████████▉ | 70/78 [00:54<00:06, 1.27it/s] 91%|█████████ | 71/78 [00:55<00:05, 1.27it/s] 92%|█████████▏| 72/78 [00:56<00:04, 1.27it/s] 94%|█████████▎| 73/78 [00:57<00:03, 1.27it/s] 95%|█████████▍| 74/78 [00:58<00:03, 1.27it/s] 96%|█████████▌| 75/78 [00:58<00:02, 1.27it/s] 97%|█████████▋| 76/78 [00:59<00:01, 1.27it/s] 99%|█████████▊| 77/78 [01:00<00:00, 1.27it/s] 100%|██████████| 78/78 [01:01<00:00, 1.27it/s] 100%|██████████| 78/78 [01:01<00:00, 1.27it/s] 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:14, 1.47it/s] 9%|▊ | 2/23 [00:01<00:14, 1.47it/s] 13%|█▎ | 3/23 [00:02<00:13, 1.48it/s] 17%|█▋ | 4/23 [00:02<00:12, 1.48it/s] 22%|██▏ | 5/23 [00:03<00:12, 1.48it/s] 26%|██▌ | 6/23 [00:04<00:11, 1.48it/s] 30%|███ | 7/23 [00:04<00:10, 1.48it/s] 35%|███▍ | 8/23 [00:05<00:10, 1.48it/s] 39%|███▉ | 9/23 [00:06<00:09, 1.48it/s] 43%|████▎ | 10/23 [00:06<00:08, 1.48it/s] 48%|████▊ | 11/23 [00:07<00:08, 1.48it/s] 52%|█████▏ | 12/23 [00:08<00:07, 1.48it/s] 57%|█████▋ | 13/23 [00:08<00:06, 1.48it/s] 61%|██████ | 14/23 [00:09<00:06, 1.48it/s] 65%|██████▌ | 15/23 [00:10<00:05, 1.48it/s] 70%|██████▉ | 16/23 [00:10<00:04, 1.48it/s] 74%|███████▍ | 17/23 [00:11<00:04, 1.48it/s] 78%|███████▊ | 18/23 [00:12<00:03, 1.48it/s] 83%|████████▎ | 19/23 [00:12<00:02, 1.48it/s] 87%|████████▋ | 20/23 [00:13<00:02, 1.48it/s] 91%|█████████▏| 21/23 [00:14<00:01, 1.48it/s] 96%|█████████▌| 22/23 [00:14<00:00, 1.48it/s] 100%|██████████| 23/23 [00:15<00:00, 1.48it/s] 100%|██████████| 23/23 [00:15<00:00, 1.48it/s]
Prediction
hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5ccIDlpeq353bj4tvpxlvgy2drlfqyqStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- seed
- 0
- width
- 1024
- height
- 1024
- prompt
- Show me a photorealistic image of Martine in front of a rainbow
- refine
- base_image_refiner
- scheduler
- K_EULER
- lora_scale
- 0.6
- num_outputs
- 3
- guidance_scale
- 10.75
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.69
- num_inference_steps
- 78
{ "seed": 0, "width": 1024, "height": 1024, "prompt": "Show me a photorealistic image of Martine in front of a rainbow", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 3, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 78 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run hughjsmith/martine using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", { input: { seed: 0, width: 1024, height: 1024, prompt: "Show me a photorealistic image of Martine in front of a rainbow", refine: "base_image_refiner", scheduler: "K_EULER", lora_scale: 0.6, num_outputs: 3, guidance_scale: 10.75, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", prompt_strength: 0.69, num_inference_steps: 78 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run hughjsmith/martine using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", input={ "seed": 0, "width": 1024, "height": 1024, "prompt": "Show me a photorealistic image of Martine in front of a rainbow", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 3, "guidance_scale": 10.75, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 78 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run hughjsmith/martine 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": "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", "input": { "seed": 0, "width": 1024, "height": 1024, "prompt": "Show me a photorealistic image of Martine in front of a rainbow", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 3, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 78 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-28T01:29:46.584859Z", "created_at": "2024-01-28T01:28:14.126529Z", "data_removed": false, "error": null, "id": "lpeq353bj4tvpxlvgy2drlfqyq", "input": { "seed": 0, "width": 1024, "height": 1024, "prompt": "Show me a photorealistic image of Martine in front of a rainbow", "refine": "base_image_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 3, "guidance_scale": 10.75, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 78 }, "logs": "Using seed: 0\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: Show me a photorealistic image of Martine in front of a rainbow\ntxt2img mode\n 0%| | 0/78 [00:00<?, ?it/s]\n 1%|▏ | 1/78 [00:00<00:59, 1.28it/s]\n 3%|▎ | 2/78 [00:01<00:59, 1.28it/s]\n 4%|▍ | 3/78 [00:02<00:58, 1.28it/s]\n 5%|▌ | 4/78 [00:03<00:57, 1.28it/s]\n 6%|▋ | 5/78 [00:03<00:56, 1.28it/s]\n 8%|▊ | 6/78 [00:04<00:56, 1.28it/s]\n 9%|▉ | 7/78 [00:05<00:55, 1.28it/s]\n 10%|█ | 8/78 [00:06<00:54, 1.28it/s]\n 12%|█▏ | 9/78 [00:07<00:54, 1.28it/s]\n 13%|█▎ | 10/78 [00:07<00:53, 1.28it/s]\n 14%|█▍ | 11/78 [00:08<00:52, 1.28it/s]\n 15%|█▌ | 12/78 [00:09<00:51, 1.28it/s]\n 17%|█▋ | 13/78 [00:10<00:50, 1.28it/s]\n 18%|█▊ | 14/78 [00:10<00:50, 1.28it/s]\n 19%|█▉ | 15/78 [00:11<00:49, 1.28it/s]\n 21%|██ | 16/78 [00:12<00:48, 1.28it/s]\n 22%|██▏ | 17/78 [00:13<00:47, 1.28it/s]\n 23%|██▎ | 18/78 [00:14<00:47, 1.28it/s]\n 24%|██▍ | 19/78 [00:14<00:46, 1.28it/s]\n 26%|██▌ | 20/78 [00:15<00:45, 1.28it/s]\n 27%|██▋ | 21/78 [00:16<00:44, 1.28it/s]\n 28%|██▊ | 22/78 [00:17<00:43, 1.27it/s]\n 29%|██▉ | 23/78 [00:18<00:43, 1.28it/s]\n 31%|███ | 24/78 [00:18<00:42, 1.28it/s]\n 32%|███▏ | 25/78 [00:19<00:41, 1.27it/s]\n 33%|███▎ | 26/78 [00:20<00:40, 1.27it/s]\n 35%|███▍ | 27/78 [00:21<00:40, 1.27it/s]\n 36%|███▌ | 28/78 [00:21<00:39, 1.27it/s]\n 37%|███▋ | 29/78 [00:22<00:38, 1.27it/s]\n 38%|███▊ | 30/78 [00:23<00:37, 1.27it/s]\n 40%|███▉ | 31/78 [00:24<00:36, 1.27it/s]\n 41%|████ | 32/78 [00:25<00:36, 1.27it/s]\n 42%|████▏ | 33/78 [00:25<00:35, 1.27it/s]\n 44%|████▎ | 34/78 [00:26<00:34, 1.27it/s]\n 45%|████▍ | 35/78 [00:27<00:33, 1.27it/s]\n 46%|████▌ | 36/78 [00:28<00:32, 1.27it/s]\n 47%|████▋ | 37/78 [00:29<00:32, 1.27it/s]\n 49%|████▊ | 38/78 [00:29<00:31, 1.27it/s]\n 50%|█████ | 39/78 [00:30<00:30, 1.27it/s]\n 51%|█████▏ | 40/78 [00:31<00:29, 1.28it/s]\n 53%|█████▎ | 41/78 [00:32<00:29, 1.27it/s]\n 54%|█████▍ | 42/78 [00:32<00:28, 1.27it/s]\n 55%|█████▌ | 43/78 [00:33<00:27, 1.27it/s]\n 56%|█████▋ | 44/78 [00:34<00:26, 1.27it/s]\n 58%|█████▊ | 45/78 [00:35<00:25, 1.28it/s]\n 59%|█████▉ | 46/78 [00:36<00:25, 1.27it/s]\n 60%|██████ | 47/78 [00:36<00:24, 1.27it/s]\n 62%|██████▏ | 48/78 [00:37<00:23, 1.27it/s]\n 63%|██████▎ | 49/78 [00:38<00:22, 1.27it/s]\n 64%|██████▍ | 50/78 [00:39<00:22, 1.27it/s]\n 65%|██████▌ | 51/78 [00:39<00:21, 1.27it/s]\n 67%|██████▋ | 52/78 [00:40<00:20, 1.27it/s]\n 68%|██████▊ | 53/78 [00:41<00:19, 1.27it/s]\n 69%|██████▉ | 54/78 [00:42<00:18, 1.27it/s]\n 71%|███████ | 55/78 [00:43<00:18, 1.27it/s]\n 72%|███████▏ | 56/78 [00:43<00:17, 1.27it/s]\n 73%|███████▎ | 57/78 [00:44<00:16, 1.27it/s]\n 74%|███████▍ | 58/78 [00:45<00:15, 1.27it/s]\n 76%|███████▌ | 59/78 [00:46<00:14, 1.27it/s]\n 77%|███████▋ | 60/78 [00:47<00:14, 1.27it/s]\n 78%|███████▊ | 61/78 [00:47<00:13, 1.27it/s]\n 79%|███████▉ | 62/78 [00:48<00:12, 1.27it/s]\n 81%|████████ | 63/78 [00:49<00:11, 1.27it/s]\n 82%|████████▏ | 64/78 [00:50<00:10, 1.27it/s]\n 83%|████████▎ | 65/78 [00:50<00:10, 1.27it/s]\n 85%|████████▍ | 66/78 [00:51<00:09, 1.27it/s]\n 86%|████████▌ | 67/78 [00:52<00:08, 1.27it/s]\n 87%|████████▋ | 68/78 [00:53<00:07, 1.27it/s]\n 88%|████████▊ | 69/78 [00:54<00:07, 1.27it/s]\n 90%|████████▉ | 70/78 [00:54<00:06, 1.27it/s]\n 91%|█████████ | 71/78 [00:55<00:05, 1.27it/s]\n 92%|█████████▏| 72/78 [00:56<00:04, 1.27it/s]\n 94%|█████████▎| 73/78 [00:57<00:03, 1.27it/s]\n 95%|█████████▍| 74/78 [00:58<00:03, 1.27it/s]\n 96%|█████████▌| 75/78 [00:58<00:02, 1.27it/s]\n 97%|█████████▋| 76/78 [00:59<00:01, 1.27it/s]\n 99%|█████████▊| 77/78 [01:00<00:00, 1.27it/s]\n100%|██████████| 78/78 [01:01<00:00, 1.27it/s]\n100%|██████████| 78/78 [01:01<00:00, 1.27it/s]\n 0%| | 0/23 [00:00<?, ?it/s]\n 4%|▍ | 1/23 [00:00<00:14, 1.47it/s]\n 9%|▊ | 2/23 [00:01<00:14, 1.47it/s]\n 13%|█▎ | 3/23 [00:02<00:13, 1.48it/s]\n 17%|█▋ | 4/23 [00:02<00:12, 1.48it/s]\n 22%|██▏ | 5/23 [00:03<00:12, 1.48it/s]\n 26%|██▌ | 6/23 [00:04<00:11, 1.48it/s]\n 30%|███ | 7/23 [00:04<00:10, 1.48it/s]\n 35%|███▍ | 8/23 [00:05<00:10, 1.48it/s]\n 39%|███▉ | 9/23 [00:06<00:09, 1.48it/s]\n 43%|████▎ | 10/23 [00:06<00:08, 1.48it/s]\n 48%|████▊ | 11/23 [00:07<00:08, 1.48it/s]\n 52%|█████▏ | 12/23 [00:08<00:07, 1.48it/s]\n 57%|█████▋ | 13/23 [00:08<00:06, 1.48it/s]\n 61%|██████ | 14/23 [00:09<00:06, 1.48it/s]\n 65%|██████▌ | 15/23 [00:10<00:05, 1.48it/s]\n 70%|██████▉ | 16/23 [00:10<00:04, 1.48it/s]\n 74%|███████▍ | 17/23 [00:11<00:04, 1.48it/s]\n 78%|███████▊ | 18/23 [00:12<00:03, 1.48it/s]\n 83%|████████▎ | 19/23 [00:12<00:02, 1.48it/s]\n 87%|████████▋ | 20/23 [00:13<00:02, 1.48it/s]\n 91%|█████████▏| 21/23 [00:14<00:01, 1.48it/s]\n 96%|█████████▌| 22/23 [00:14<00:00, 1.48it/s]\n100%|██████████| 23/23 [00:15<00:00, 1.48it/s]\n100%|██████████| 23/23 [00:15<00:00, 1.48it/s]", "metrics": { "predict_time": 82.177495, "total_time": 92.45833 }, "output": [ "https://replicate.delivery/pbxt/i7WedFndhFwzKKLGo4TEs4qWwfppxSeh8eZigovtBLslAYDJB/out-0.png", "https://replicate.delivery/pbxt/XOgcE6isfd2aVyDNBOwFGGQFv11SBtTvwgGFIagevVEJA2QSA/out-1.png", "https://replicate.delivery/pbxt/UsXXVe1ANPUpbSNsW9T8auPVlfZLDFfSv8dYzfYc42cpAYDJB/out-2.png" ], "started_at": "2024-01-28T01:28:24.407364Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/lpeq353bj4tvpxlvgy2drlfqyq", "cancel": "https://api.replicate.com/v1/predictions/lpeq353bj4tvpxlvgy2drlfqyq/cancel" }, "version": "6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc" }
Generated inUsing seed: 0 Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: Show me a photorealistic image of Martine in front of a rainbow txt2img mode 0%| | 0/78 [00:00<?, ?it/s] 1%|▏ | 1/78 [00:00<00:59, 1.28it/s] 3%|▎ | 2/78 [00:01<00:59, 1.28it/s] 4%|▍ | 3/78 [00:02<00:58, 1.28it/s] 5%|▌ | 4/78 [00:03<00:57, 1.28it/s] 6%|▋ | 5/78 [00:03<00:56, 1.28it/s] 8%|▊ | 6/78 [00:04<00:56, 1.28it/s] 9%|▉ | 7/78 [00:05<00:55, 1.28it/s] 10%|█ | 8/78 [00:06<00:54, 1.28it/s] 12%|█▏ | 9/78 [00:07<00:54, 1.28it/s] 13%|█▎ | 10/78 [00:07<00:53, 1.28it/s] 14%|█▍ | 11/78 [00:08<00:52, 1.28it/s] 15%|█▌ | 12/78 [00:09<00:51, 1.28it/s] 17%|█▋ | 13/78 [00:10<00:50, 1.28it/s] 18%|█▊ | 14/78 [00:10<00:50, 1.28it/s] 19%|█▉ | 15/78 [00:11<00:49, 1.28it/s] 21%|██ | 16/78 [00:12<00:48, 1.28it/s] 22%|██▏ | 17/78 [00:13<00:47, 1.28it/s] 23%|██▎ | 18/78 [00:14<00:47, 1.28it/s] 24%|██▍ | 19/78 [00:14<00:46, 1.28it/s] 26%|██▌ | 20/78 [00:15<00:45, 1.28it/s] 27%|██▋ | 21/78 [00:16<00:44, 1.28it/s] 28%|██▊ | 22/78 [00:17<00:43, 1.27it/s] 29%|██▉ | 23/78 [00:18<00:43, 1.28it/s] 31%|███ | 24/78 [00:18<00:42, 1.28it/s] 32%|███▏ | 25/78 [00:19<00:41, 1.27it/s] 33%|███▎ | 26/78 [00:20<00:40, 1.27it/s] 35%|███▍ | 27/78 [00:21<00:40, 1.27it/s] 36%|███▌ | 28/78 [00:21<00:39, 1.27it/s] 37%|███▋ | 29/78 [00:22<00:38, 1.27it/s] 38%|███▊ | 30/78 [00:23<00:37, 1.27it/s] 40%|███▉ | 31/78 [00:24<00:36, 1.27it/s] 41%|████ | 32/78 [00:25<00:36, 1.27it/s] 42%|████▏ | 33/78 [00:25<00:35, 1.27it/s] 44%|████▎ | 34/78 [00:26<00:34, 1.27it/s] 45%|████▍ | 35/78 [00:27<00:33, 1.27it/s] 46%|████▌ | 36/78 [00:28<00:32, 1.27it/s] 47%|████▋ | 37/78 [00:29<00:32, 1.27it/s] 49%|████▊ | 38/78 [00:29<00:31, 1.27it/s] 50%|█████ | 39/78 [00:30<00:30, 1.27it/s] 51%|█████▏ | 40/78 [00:31<00:29, 1.28it/s] 53%|█████▎ | 41/78 [00:32<00:29, 1.27it/s] 54%|█████▍ | 42/78 [00:32<00:28, 1.27it/s] 55%|█████▌ | 43/78 [00:33<00:27, 1.27it/s] 56%|█████▋ | 44/78 [00:34<00:26, 1.27it/s] 58%|█████▊ | 45/78 [00:35<00:25, 1.28it/s] 59%|█████▉ | 46/78 [00:36<00:25, 1.27it/s] 60%|██████ | 47/78 [00:36<00:24, 1.27it/s] 62%|██████▏ | 48/78 [00:37<00:23, 1.27it/s] 63%|██████▎ | 49/78 [00:38<00:22, 1.27it/s] 64%|██████▍ | 50/78 [00:39<00:22, 1.27it/s] 65%|██████▌ | 51/78 [00:39<00:21, 1.27it/s] 67%|██████▋ | 52/78 [00:40<00:20, 1.27it/s] 68%|██████▊ | 53/78 [00:41<00:19, 1.27it/s] 69%|██████▉ | 54/78 [00:42<00:18, 1.27it/s] 71%|███████ | 55/78 [00:43<00:18, 1.27it/s] 72%|███████▏ | 56/78 [00:43<00:17, 1.27it/s] 73%|███████▎ | 57/78 [00:44<00:16, 1.27it/s] 74%|███████▍ | 58/78 [00:45<00:15, 1.27it/s] 76%|███████▌ | 59/78 [00:46<00:14, 1.27it/s] 77%|███████▋ | 60/78 [00:47<00:14, 1.27it/s] 78%|███████▊ | 61/78 [00:47<00:13, 1.27it/s] 79%|███████▉ | 62/78 [00:48<00:12, 1.27it/s] 81%|████████ | 63/78 [00:49<00:11, 1.27it/s] 82%|████████▏ | 64/78 [00:50<00:10, 1.27it/s] 83%|████████▎ | 65/78 [00:50<00:10, 1.27it/s] 85%|████████▍ | 66/78 [00:51<00:09, 1.27it/s] 86%|████████▌ | 67/78 [00:52<00:08, 1.27it/s] 87%|████████▋ | 68/78 [00:53<00:07, 1.27it/s] 88%|████████▊ | 69/78 [00:54<00:07, 1.27it/s] 90%|████████▉ | 70/78 [00:54<00:06, 1.27it/s] 91%|█████████ | 71/78 [00:55<00:05, 1.27it/s] 92%|█████████▏| 72/78 [00:56<00:04, 1.27it/s] 94%|█████████▎| 73/78 [00:57<00:03, 1.27it/s] 95%|█████████▍| 74/78 [00:58<00:03, 1.27it/s] 96%|█████████▌| 75/78 [00:58<00:02, 1.27it/s] 97%|█████████▋| 76/78 [00:59<00:01, 1.27it/s] 99%|█████████▊| 77/78 [01:00<00:00, 1.27it/s] 100%|██████████| 78/78 [01:01<00:00, 1.27it/s] 100%|██████████| 78/78 [01:01<00:00, 1.27it/s] 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:14, 1.47it/s] 9%|▊ | 2/23 [00:01<00:14, 1.47it/s] 13%|█▎ | 3/23 [00:02<00:13, 1.48it/s] 17%|█▋ | 4/23 [00:02<00:12, 1.48it/s] 22%|██▏ | 5/23 [00:03<00:12, 1.48it/s] 26%|██▌ | 6/23 [00:04<00:11, 1.48it/s] 30%|███ | 7/23 [00:04<00:10, 1.48it/s] 35%|███▍ | 8/23 [00:05<00:10, 1.48it/s] 39%|███▉ | 9/23 [00:06<00:09, 1.48it/s] 43%|████▎ | 10/23 [00:06<00:08, 1.48it/s] 48%|████▊ | 11/23 [00:07<00:08, 1.48it/s] 52%|█████▏ | 12/23 [00:08<00:07, 1.48it/s] 57%|█████▋ | 13/23 [00:08<00:06, 1.48it/s] 61%|██████ | 14/23 [00:09<00:06, 1.48it/s] 65%|██████▌ | 15/23 [00:10<00:05, 1.48it/s] 70%|██████▉ | 16/23 [00:10<00:04, 1.48it/s] 74%|███████▍ | 17/23 [00:11<00:04, 1.48it/s] 78%|███████▊ | 18/23 [00:12<00:03, 1.48it/s] 83%|████████▎ | 19/23 [00:12<00:02, 1.48it/s] 87%|████████▋ | 20/23 [00:13<00:02, 1.48it/s] 91%|█████████▏| 21/23 [00:14<00:01, 1.48it/s] 96%|█████████▌| 22/23 [00:14<00:00, 1.48it/s] 100%|██████████| 23/23 [00:15<00:00, 1.48it/s] 100%|██████████| 23/23 [00:15<00:00, 1.48it/s]
Prediction
hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5ccIDvqyy7i3b6snwvneihtex36jyxiStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- width
- 1024
- height
- 1024
- prompt
- An image of Martine riding a horse
- refine
- no_refiner
- scheduler
- DPMSolverMultistep
- lora_scale
- 0.6
- num_outputs
- 2
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.8
- negative_prompt
- prompt_strength
- 0.69
- num_inference_steps
- 50
{ "width": 1024, "height": 1024, "prompt": "An image of Martine riding a horse", "refine": "no_refiner", "scheduler": "DPMSolverMultistep", "lora_scale": 0.6, "num_outputs": 2, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 50 }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run hughjsmith/martine using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", { input: { width: 1024, height: 1024, prompt: "An image of Martine riding a horse", refine: "no_refiner", scheduler: "DPMSolverMultistep", lora_scale: 0.6, num_outputs: 2, guidance_scale: 7.5, apply_watermark: true, high_noise_frac: 0.8, negative_prompt: "", prompt_strength: 0.69, num_inference_steps: 50 } } ); // To access the file URL: console.log(output[0].url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run hughjsmith/martine using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", input={ "width": 1024, "height": 1024, "prompt": "An image of Martine riding a horse", "refine": "no_refiner", "scheduler": "DPMSolverMultistep", "lora_scale": 0.6, "num_outputs": 2, "guidance_scale": 7.5, "apply_watermark": True, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 50 } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run hughjsmith/martine 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": "hughjsmith/martine:6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc", "input": { "width": 1024, "height": 1024, "prompt": "An image of Martine riding a horse", "refine": "no_refiner", "scheduler": "DPMSolverMultistep", "lora_scale": 0.6, "num_outputs": 2, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 50 } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-01-28T01:40:23.419839Z", "created_at": "2024-01-28T01:39:49.136083Z", "data_removed": false, "error": null, "id": "vqyy7i3b6snwvneihtex36jyxi", "input": { "width": 1024, "height": 1024, "prompt": "An image of Martine riding a horse", "refine": "no_refiner", "scheduler": "DPMSolverMultistep", "lora_scale": 0.6, "num_outputs": 2, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.69, "num_inference_steps": 50 }, "logs": "Using seed: 47989\nEnsuring enough disk space...\nFree disk space: 1704502026240\nDownloading weights: https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar\n2024-01-28T01:39:50Z | INFO | [ Initiating ] dest=/src/weights-cache/d7925bd432f7746b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar\n2024-01-28T01:39:51Z | INFO | [ Complete ] dest=/src/weights-cache/d7925bd432f7746b size=\"186 MB\" total_elapsed=0.746s url=https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar\nb''\nDownloaded weights in 0.9696338176727295 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: An image of Martine riding a horse\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:26, 1.86it/s]\n 4%|▍ | 2/50 [00:01<00:25, 1.87it/s]\n 6%|▌ | 3/50 [00:01<00:25, 1.88it/s]\n 8%|▊ | 4/50 [00:02<00:24, 1.88it/s]\n 10%|█ | 5/50 [00:02<00:23, 1.88it/s]\n 12%|█▏ | 6/50 [00:03<00:23, 1.89it/s]\n 14%|█▍ | 7/50 [00:03<00:22, 1.89it/s]\n 16%|█▌ | 8/50 [00:04<00:22, 1.89it/s]\n 18%|█▊ | 9/50 [00:04<00:21, 1.89it/s]\n 20%|██ | 10/50 [00:05<00:21, 1.89it/s]\n 22%|██▏ | 11/50 [00:05<00:20, 1.88it/s]\n 24%|██▍ | 12/50 [00:06<00:20, 1.88it/s]\n 26%|██▌ | 13/50 [00:06<00:19, 1.88it/s]\n 28%|██▊ | 14/50 [00:07<00:19, 1.88it/s]\n 30%|███ | 15/50 [00:07<00:18, 1.88it/s]\n 32%|███▏ | 16/50 [00:08<00:18, 1.88it/s]\n 34%|███▍ | 17/50 [00:09<00:17, 1.88it/s]\n 36%|███▌ | 18/50 [00:09<00:17, 1.88it/s]\n 38%|███▊ | 19/50 [00:10<00:16, 1.88it/s]\n 40%|████ | 20/50 [00:10<00:15, 1.88it/s]\n 42%|████▏ | 21/50 [00:11<00:15, 1.88it/s]\n 44%|████▍ | 22/50 [00:11<00:14, 1.88it/s]\n 46%|████▌ | 23/50 [00:12<00:14, 1.88it/s]\n 48%|████▊ | 24/50 [00:12<00:13, 1.88it/s]\n 50%|█████ | 25/50 [00:13<00:13, 1.88it/s]\n 52%|█████▏ | 26/50 [00:13<00:12, 1.88it/s]\n 54%|█████▍ | 27/50 [00:14<00:12, 1.88it/s]\n 56%|█████▌ | 28/50 [00:14<00:11, 1.88it/s]\n 58%|█████▊ | 29/50 [00:15<00:11, 1.88it/s]\n 60%|██████ | 30/50 [00:15<00:10, 1.88it/s]\n 62%|██████▏ | 31/50 [00:16<00:10, 1.88it/s]\n 64%|██████▍ | 32/50 [00:17<00:09, 1.88it/s]\n 66%|██████▌ | 33/50 [00:17<00:09, 1.87it/s]\n 68%|██████▊ | 34/50 [00:18<00:08, 1.87it/s]\n 70%|███████ | 35/50 [00:18<00:08, 1.87it/s]\n 72%|███████▏ | 36/50 [00:19<00:07, 1.87it/s]\n 74%|███████▍ | 37/50 [00:19<00:06, 1.87it/s]\n 76%|███████▌ | 38/50 [00:20<00:06, 1.87it/s]\n 78%|███████▊ | 39/50 [00:20<00:05, 1.87it/s]\n 80%|████████ | 40/50 [00:21<00:05, 1.87it/s]\n 82%|████████▏ | 41/50 [00:21<00:04, 1.86it/s]\n 84%|████████▍ | 42/50 [00:22<00:04, 1.86it/s]\n 86%|████████▌ | 43/50 [00:22<00:03, 1.87it/s]\n 88%|████████▊ | 44/50 [00:23<00:03, 1.87it/s]\n 90%|█████████ | 45/50 [00:23<00:02, 1.87it/s]\n 92%|█████████▏| 46/50 [00:24<00:02, 1.87it/s]\n 94%|█████████▍| 47/50 [00:25<00:01, 1.87it/s]\n 96%|█████████▌| 48/50 [00:25<00:01, 1.87it/s]\n 98%|█████████▊| 49/50 [00:26<00:00, 1.87it/s]\n100%|██████████| 50/50 [00:26<00:00, 1.87it/s]\n100%|██████████| 50/50 [00:26<00:00, 1.88it/s]", "metrics": { "predict_time": 32.641354, "total_time": 34.283756 }, "output": [ "https://replicate.delivery/pbxt/ucbyaPhYW7oLEdaouyWKzTbiGpHwQ9VmS4sgys5K6vchiNkE/out-0.png", "https://replicate.delivery/pbxt/kBye0DbK81xVNiiPuDlXi1l65SV6c5R8sNvuhQihXkhDFbIJA/out-1.png" ], "started_at": "2024-01-28T01:39:50.778485Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/vqyy7i3b6snwvneihtex36jyxi", "cancel": "https://api.replicate.com/v1/predictions/vqyy7i3b6snwvneihtex36jyxi/cancel" }, "version": "6dde1a92312fbe518cbe5ae63ee6cb93dd2fc933b9a3f9e88b4f763f4073d5cc" }
Generated inUsing seed: 47989 Ensuring enough disk space... Free disk space: 1704502026240 Downloading weights: https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar 2024-01-28T01:39:50Z | INFO | [ Initiating ] dest=/src/weights-cache/d7925bd432f7746b minimum_chunk_size=150M url=https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar 2024-01-28T01:39:51Z | INFO | [ Complete ] dest=/src/weights-cache/d7925bd432f7746b size="186 MB" total_elapsed=0.746s url=https://replicate.delivery/pbxt/mMPaZnYwzWJdNxao7DtsSTgWjMU16tIzplQV2og0FLfb2wBJA/trained_model.tar b'' Downloaded weights in 0.9696338176727295 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: An image of Martine riding a horse txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:26, 1.86it/s] 4%|▍ | 2/50 [00:01<00:25, 1.87it/s] 6%|▌ | 3/50 [00:01<00:25, 1.88it/s] 8%|▊ | 4/50 [00:02<00:24, 1.88it/s] 10%|█ | 5/50 [00:02<00:23, 1.88it/s] 12%|█▏ | 6/50 [00:03<00:23, 1.89it/s] 14%|█▍ | 7/50 [00:03<00:22, 1.89it/s] 16%|█▌ | 8/50 [00:04<00:22, 1.89it/s] 18%|█▊ | 9/50 [00:04<00:21, 1.89it/s] 20%|██ | 10/50 [00:05<00:21, 1.89it/s] 22%|██▏ | 11/50 [00:05<00:20, 1.88it/s] 24%|██▍ | 12/50 [00:06<00:20, 1.88it/s] 26%|██▌ | 13/50 [00:06<00:19, 1.88it/s] 28%|██▊ | 14/50 [00:07<00:19, 1.88it/s] 30%|███ | 15/50 [00:07<00:18, 1.88it/s] 32%|███▏ | 16/50 [00:08<00:18, 1.88it/s] 34%|███▍ | 17/50 [00:09<00:17, 1.88it/s] 36%|███▌ | 18/50 [00:09<00:17, 1.88it/s] 38%|███▊ | 19/50 [00:10<00:16, 1.88it/s] 40%|████ | 20/50 [00:10<00:15, 1.88it/s] 42%|████▏ | 21/50 [00:11<00:15, 1.88it/s] 44%|████▍ | 22/50 [00:11<00:14, 1.88it/s] 46%|████▌ | 23/50 [00:12<00:14, 1.88it/s] 48%|████▊ | 24/50 [00:12<00:13, 1.88it/s] 50%|█████ | 25/50 [00:13<00:13, 1.88it/s] 52%|█████▏ | 26/50 [00:13<00:12, 1.88it/s] 54%|█████▍ | 27/50 [00:14<00:12, 1.88it/s] 56%|█████▌ | 28/50 [00:14<00:11, 1.88it/s] 58%|█████▊ | 29/50 [00:15<00:11, 1.88it/s] 60%|██████ | 30/50 [00:15<00:10, 1.88it/s] 62%|██████▏ | 31/50 [00:16<00:10, 1.88it/s] 64%|██████▍ | 32/50 [00:17<00:09, 1.88it/s] 66%|██████▌ | 33/50 [00:17<00:09, 1.87it/s] 68%|██████▊ | 34/50 [00:18<00:08, 1.87it/s] 70%|███████ | 35/50 [00:18<00:08, 1.87it/s] 72%|███████▏ | 36/50 [00:19<00:07, 1.87it/s] 74%|███████▍ | 37/50 [00:19<00:06, 1.87it/s] 76%|███████▌ | 38/50 [00:20<00:06, 1.87it/s] 78%|███████▊ | 39/50 [00:20<00:05, 1.87it/s] 80%|████████ | 40/50 [00:21<00:05, 1.87it/s] 82%|████████▏ | 41/50 [00:21<00:04, 1.86it/s] 84%|████████▍ | 42/50 [00:22<00:04, 1.86it/s] 86%|████████▌ | 43/50 [00:22<00:03, 1.87it/s] 88%|████████▊ | 44/50 [00:23<00:03, 1.87it/s] 90%|█████████ | 45/50 [00:23<00:02, 1.87it/s] 92%|█████████▏| 46/50 [00:24<00:02, 1.87it/s] 94%|█████████▍| 47/50 [00:25<00:01, 1.87it/s] 96%|█████████▌| 48/50 [00:25<00:01, 1.87it/s] 98%|█████████▊| 49/50 [00:26<00:00, 1.87it/s] 100%|██████████| 50/50 [00:26<00:00, 1.87it/s] 100%|██████████| 50/50 [00:26<00:00, 1.88it/s]
Want to make some of these yourself?
Run this model