lucataco / wan2.1-i2v-lora
Wan2.1 14B 480p LoRA inference via Diffusers (Work in progress)
Prediction
lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97ID7qeh90jf09rj20cnk2asj5vbrcStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedby @lucatacoInput
- fps
- 16
- image
- prompt
- The video features a wooden chair with a blue cushion doing a r0t4tion 360 degrees rotation.
- duration
- 5
- lora_url
- https://huggingface.co/Remade-AI/Rotate/resolve/main/rotate_20_epochs.safetensors
- resize_mode
- auto
- lora_strength
- 1
- guidance_scale
- 5
- negative_prompt
- low quality, bad quality, blurry, pixelated, watermark
- num_inference_steps
- 40
{ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf7iYw4Th9uGwICuCMBbaEjlDWAoTTSyP1WbhVlIzda1iSs2/Screenshot%202025-03-15%20at%202.54.22%E2%80%AFAM.png", "prompt": "The video features a wooden chair with a blue cushion doing a r0t4tion 360 degrees rotation.", "duration": 5, "lora_url": "https://huggingface.co/Remade-AI/Rotate/resolve/main/rotate_20_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport 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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", { input: { fps: 16, image: "https://replicate.delivery/pbxt/Mf7iYw4Th9uGwICuCMBbaEjlDWAoTTSyP1WbhVlIzda1iSs2/Screenshot%202025-03-15%20at%202.54.22%E2%80%AFAM.png", prompt: "The video features a wooden chair with a blue cushion doing a r0t4tion 360 degrees rotation.", duration: 5, lora_url: "https://huggingface.co/Remade-AI/Rotate/resolve/main/rotate_20_epochs.safetensors", resize_mode: "auto", lora_strength: 1, guidance_scale: 5, negative_prompt: "low quality, bad quality, blurry, pixelated, watermark", num_inference_steps: 40 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", input={ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf7iYw4Th9uGwICuCMBbaEjlDWAoTTSyP1WbhVlIzda1iSs2/Screenshot%202025-03-15%20at%202.54.22%E2%80%AFAM.png", "prompt": "The video features a wooden chair with a blue cushion doing a r0t4tion 360 degrees rotation.", "duration": 5, "lora_url": "https://huggingface.co/Remade-AI/Rotate/resolve/main/rotate_20_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/wan2.1-i2v-lora 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": "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf7iYw4Th9uGwICuCMBbaEjlDWAoTTSyP1WbhVlIzda1iSs2/Screenshot%202025-03-15%20at%202.54.22%E2%80%AFAM.png", "prompt": "The video features a wooden chair with a blue cushion doing a r0t4tion 360 degrees rotation.", "duration": 5, "lora_url": "https://huggingface.co/Remade-AI/Rotate/resolve/main/rotate_20_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-03-15T07:02:58.051715Z", "created_at": "2025-03-15T06:54:36.802000Z", "data_removed": false, "error": null, "id": "7qeh90jf09rj20cnk2asj5vbrc", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf7iYw4Th9uGwICuCMBbaEjlDWAoTTSyP1WbhVlIzda1iSs2/Screenshot%202025-03-15%20at%202.54.22%E2%80%AFAM.png", "prompt": "The video features a wooden chair with a blue cushion doing a r0t4tion 360 degrees rotation.", "duration": 5, "lora_url": "https://huggingface.co/Remade-AI/Rotate/resolve/main/rotate_20_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }, "logs": "Starting prediction with: prompt='The video features a wooden chair with a blue cushion doing a r0t4tion 360 degrees rotation.', lora_strength=1.0, duration=5.0s\nCalculated 81 frames for 5.0s at 16 fps\nLoading input image from: /tmp/tmpk82sgfvwScreenshot 2025-03-15 at 2.54.22 AM.png\nImage loaded successfully: 928x881\nAuto-selected fixed square dimensions: 512x512 for aspect ratio 0.95\nFinal dimensions: 512x512\nDownloading LoRA from: https://huggingface.co/Remade-AI/Rotate/resolve/main/rotate_20_epochs.safetensors\nDownloading from HuggingFace: repo_id=Remade-AI/Rotate, filename=rotate_20_epochs.safetensors\nLoading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Rotate/snapshots/76002e729d475e9142a217ab9f63107a7dda950c/rotate_20_epochs.safetensors with strength: 1.0\nLoRA weights loaded successfully\nStarting video generation: 81 frames, 40 steps, guidance=5.0\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:10<07:04, 10.89s/it]\n 5%|▌ | 2/40 [00:20<06:32, 10.32s/it]\n 8%|▊ | 3/40 [00:31<06:32, 10.60s/it]\n 10%|█ | 4/40 [00:42<06:26, 10.74s/it]\n 12%|█▎ | 5/40 [00:53<06:18, 10.82s/it]\n 15%|█▌ | 6/40 [01:04<06:09, 10.87s/it]\n 18%|█▊ | 7/40 [01:15<05:59, 10.90s/it]\n 20%|██ | 8/40 [01:26<05:49, 10.92s/it]\n 22%|██▎ | 9/40 [01:37<05:39, 10.94s/it]\n 25%|██▌ | 10/40 [01:48<05:28, 10.95s/it]\n 28%|██▊ | 11/40 [01:59<05:17, 10.96s/it]\n 30%|███ | 12/40 [02:10<05:06, 10.96s/it]\n 32%|███▎ | 13/40 [02:21<04:56, 10.97s/it]\n 35%|███▌ | 14/40 [02:32<04:45, 10.97s/it]\n 38%|███▊ | 15/40 [02:43<04:34, 10.97s/it]\n 40%|████ | 16/40 [02:54<04:23, 10.97s/it]\n 42%|████▎ | 17/40 [03:05<04:12, 10.97s/it]\n 45%|████▌ | 18/40 [03:16<04:01, 10.97s/it]\n 48%|████▊ | 19/40 [03:27<03:50, 10.97s/it]\n 50%|█████ | 20/40 [03:38<03:39, 10.97s/it]\n 52%|█████▎ | 21/40 [03:49<03:28, 10.97s/it]\n 55%|█████▌ | 22/40 [04:00<03:17, 10.97s/it]\n 57%|█████▊ | 23/40 [04:11<03:06, 10.97s/it]\n 60%|██████ | 24/40 [04:22<02:55, 10.97s/it]\n 62%|██████▎ | 25/40 [04:33<02:44, 10.97s/it]\n 65%|██████▌ | 26/40 [04:44<02:33, 10.97s/it]\n 68%|██████▊ | 27/40 [04:55<02:22, 10.97s/it]\n 70%|███████ | 28/40 [05:06<02:11, 10.97s/it]\n 72%|███████▎ | 29/40 [05:16<02:00, 10.97s/it]\n 75%|███████▌ | 30/40 [05:27<01:49, 10.96s/it]\n 78%|███████▊ | 31/40 [05:38<01:38, 10.96s/it]\n 80%|████████ | 32/40 [05:49<01:27, 10.96s/it]\n 82%|████████▎ | 33/40 [06:00<01:16, 10.96s/it]\n 85%|████████▌ | 34/40 [06:11<01:05, 10.96s/it]\n 88%|████████▊ | 35/40 [06:22<00:54, 10.96s/it]\n 90%|█████████ | 36/40 [06:33<00:43, 10.96s/it]\n 92%|█████████▎| 37/40 [06:44<00:32, 10.96s/it]\n 95%|█████████▌| 38/40 [06:55<00:21, 10.96s/it]\n 98%|█████████▊| 39/40 [07:06<00:10, 10.96s/it]\n100%|██████████| 40/40 [07:17<00:00, 10.96s/it]\n100%|██████████| 40/40 [07:17<00:00, 10.94s/it]\nVideo generation completed in 445.07 seconds\nExporting video to: /tmp/tmpz0y1cuwd/output.mp4 at 16 fps\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVideo saved successfully to: /tmp/tmpz0y1cuwd/output.mp4\nCleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Rotate/snapshots/76002e729d475e9142a217ab9f63107a7dda950c/rotate_20_epochs.safetensors", "metrics": { "predict_time": 448.201368672, "total_time": 501.249715 }, "output": "https://replicate.delivery/yhqm/fdcwBGRjYLWlJa1j2qmftwg77ZeRcSCHXZfcjyh2DkMJC2iRB/output.mp4", "started_at": "2025-03-15T06:55:29.850347Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/yswh-2reuou4i77a4cio2g463crcc4ij3wi5po4vevutstaezg5sqs7wq", "get": "https://api.replicate.com/v1/predictions/7qeh90jf09rj20cnk2asj5vbrc", "cancel": "https://api.replicate.com/v1/predictions/7qeh90jf09rj20cnk2asj5vbrc/cancel" }, "version": "f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97" }Generated inStarting prediction with: prompt='The video features a wooden chair with a blue cushion doing a r0t4tion 360 degrees rotation.', lora_strength=1.0, duration=5.0s Calculated 81 frames for 5.0s at 16 fps Loading input image from: /tmp/tmpk82sgfvwScreenshot 2025-03-15 at 2.54.22 AM.png Image loaded successfully: 928x881 Auto-selected fixed square dimensions: 512x512 for aspect ratio 0.95 Final dimensions: 512x512 Downloading LoRA from: https://huggingface.co/Remade-AI/Rotate/resolve/main/rotate_20_epochs.safetensors Downloading from HuggingFace: repo_id=Remade-AI/Rotate, filename=rotate_20_epochs.safetensors Loading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Rotate/snapshots/76002e729d475e9142a217ab9f63107a7dda950c/rotate_20_epochs.safetensors with strength: 1.0 LoRA weights loaded successfully Starting video generation: 81 frames, 40 steps, guidance=5.0 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:10<07:04, 10.89s/it] 5%|▌ | 2/40 [00:20<06:32, 10.32s/it] 8%|▊ | 3/40 [00:31<06:32, 10.60s/it] 10%|█ | 4/40 [00:42<06:26, 10.74s/it] 12%|█▎ | 5/40 [00:53<06:18, 10.82s/it] 15%|█▌ | 6/40 [01:04<06:09, 10.87s/it] 18%|█▊ | 7/40 [01:15<05:59, 10.90s/it] 20%|██ | 8/40 [01:26<05:49, 10.92s/it] 22%|██▎ | 9/40 [01:37<05:39, 10.94s/it] 25%|██▌ | 10/40 [01:48<05:28, 10.95s/it] 28%|██▊ | 11/40 [01:59<05:17, 10.96s/it] 30%|███ | 12/40 [02:10<05:06, 10.96s/it] 32%|███▎ | 13/40 [02:21<04:56, 10.97s/it] 35%|███▌ | 14/40 [02:32<04:45, 10.97s/it] 38%|███▊ | 15/40 [02:43<04:34, 10.97s/it] 40%|████ | 16/40 [02:54<04:23, 10.97s/it] 42%|████▎ | 17/40 [03:05<04:12, 10.97s/it] 45%|████▌ | 18/40 [03:16<04:01, 10.97s/it] 48%|████▊ | 19/40 [03:27<03:50, 10.97s/it] 50%|█████ | 20/40 [03:38<03:39, 10.97s/it] 52%|█████▎ | 21/40 [03:49<03:28, 10.97s/it] 55%|█████▌ | 22/40 [04:00<03:17, 10.97s/it] 57%|█████▊ | 23/40 [04:11<03:06, 10.97s/it] 60%|██████ | 24/40 [04:22<02:55, 10.97s/it] 62%|██████▎ | 25/40 [04:33<02:44, 10.97s/it] 65%|██████▌ | 26/40 [04:44<02:33, 10.97s/it] 68%|██████▊ | 27/40 [04:55<02:22, 10.97s/it] 70%|███████ | 28/40 [05:06<02:11, 10.97s/it] 72%|███████▎ | 29/40 [05:16<02:00, 10.97s/it] 75%|███████▌ | 30/40 [05:27<01:49, 10.96s/it] 78%|███████▊ | 31/40 [05:38<01:38, 10.96s/it] 80%|████████ | 32/40 [05:49<01:27, 10.96s/it] 82%|████████▎ | 33/40 [06:00<01:16, 10.96s/it] 85%|████████▌ | 34/40 [06:11<01:05, 10.96s/it] 88%|████████▊ | 35/40 [06:22<00:54, 10.96s/it] 90%|█████████ | 36/40 [06:33<00:43, 10.96s/it] 92%|█████████▎| 37/40 [06:44<00:32, 10.96s/it] 95%|█████████▌| 38/40 [06:55<00:21, 10.96s/it] 98%|█████████▊| 39/40 [07:06<00:10, 10.96s/it] 100%|██████████| 40/40 [07:17<00:00, 10.96s/it] 100%|██████████| 40/40 [07:17<00:00, 10.94s/it] Video generation completed in 445.07 seconds Exporting video to: /tmp/tmpz0y1cuwd/output.mp4 at 16 fps huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Video saved successfully to: /tmp/tmpz0y1cuwd/output.mp4 Cleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Rotate/snapshots/76002e729d475e9142a217ab9f63107a7dda950c/rotate_20_epochs.safetensorsPrediction
lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97IDp0xwwxqvpdrj00cnk2fawv6kbrStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- fps
- 16
- image
- prompt
- In the video, a miniature dog is presented. The dog is held in a person's hands. The person then presses on the dog, causing a sq41sh squish effect. The person keeps pressing down on the dog, further showing the sq41sh squish effect.
- duration
- 3
- lora_url
- https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors
- resize_mode
- auto
- lora_strength
- 1
- guidance_scale
- 5
- negative_prompt
- low quality, bad quality, blurry, pixelated, watermark
- num_inference_steps
- 40
{ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf7Um7V1nQjebWjOi3RndihR5sK95269LxZDY8s17mqW5jda/dog-1024.png", "prompt": "In the video, a miniature dog is presented. The dog is held in a person's hands. The person then presses on the dog, causing a sq41sh squish effect. The person keeps pressing down on the dog, further showing the sq41sh squish effect.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport 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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", { input: { fps: 16, image: "https://replicate.delivery/pbxt/Mf7Um7V1nQjebWjOi3RndihR5sK95269LxZDY8s17mqW5jda/dog-1024.png", prompt: "In the video, a miniature dog is presented. The dog is held in a person's hands. The person then presses on the dog, causing a sq41sh squish effect. The person keeps pressing down on the dog, further showing the sq41sh squish effect.", duration: 3, lora_url: "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", resize_mode: "auto", lora_strength: 1, guidance_scale: 5, negative_prompt: "low quality, bad quality, blurry, pixelated, watermark", num_inference_steps: 40 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", input={ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf7Um7V1nQjebWjOi3RndihR5sK95269LxZDY8s17mqW5jda/dog-1024.png", "prompt": "In the video, a miniature dog is presented. The dog is held in a person's hands. The person then presses on the dog, causing a sq41sh squish effect. The person keeps pressing down on the dog, further showing the sq41sh squish effect.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/wan2.1-i2v-lora 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": "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf7Um7V1nQjebWjOi3RndihR5sK95269LxZDY8s17mqW5jda/dog-1024.png", "prompt": "In the video, a miniature dog is presented. The dog is held in a person\'s hands. The person then presses on the dog, causing a sq41sh squish effect. The person keeps pressing down on the dog, further showing the sq41sh squish effect.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-03-15T07:09:14.636690Z", "created_at": "2025-03-15T07:05:10.835000Z", "data_removed": false, "error": null, "id": "p0xwwxqvpdrj00cnk2fawv6kbr", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf7Um7V1nQjebWjOi3RndihR5sK95269LxZDY8s17mqW5jda/dog-1024.png", "prompt": "In the video, a miniature dog is presented. The dog is held in a person's hands. The person then presses on the dog, causing a sq41sh squish effect. The person keeps pressing down on the dog, further showing the sq41sh squish effect.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }, "logs": "Starting prediction with: prompt='In the video, a miniature dog is presented. The dog is held in a person's hands. The person then presses on the dog, causing a sq41sh squish effect. The person keeps pressing down on the dog, further showing the sq41sh squish effect.', lora_strength=1.0, duration=3.0s\nCalculated 49 frames for 3.0s at 16 fps\nLoading input image from: /tmp/tmpl6fn4nyqdog-1024.png\nImage loaded successfully: 1001x991\nAuto-selected fixed square dimensions: 512x512 for aspect ratio 0.99\nFinal dimensions: 512x512\nDownloading LoRA from: https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors\nDownloading from HuggingFace: repo_id=Remade-AI/Squish, filename=squish_18.safetensors\nLoading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Squish/snapshots/70e32c7d833743c88352e2ac973968417fb5b051/squish_18.safetensors with strength: 1.0\nLoRA weights loaded successfully\nStarting video generation: 49 frames, 40 steps, guidance=5.0\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:05<03:48, 5.87s/it]\n 5%|▌ | 2/40 [00:11<03:31, 5.55s/it]\n 8%|▊ | 3/40 [00:17<03:31, 5.71s/it]\n 10%|█ | 4/40 [00:22<03:28, 5.78s/it]\n 12%|█▎ | 5/40 [00:28<03:23, 5.82s/it]\n 15%|█▌ | 6/40 [00:34<03:19, 5.85s/it]\n 18%|█▊ | 7/40 [00:40<03:13, 5.87s/it]\n 20%|██ | 8/40 [00:46<03:08, 5.89s/it]\n 22%|██▎ | 9/40 [00:52<03:02, 5.90s/it]\n 25%|██▌ | 10/40 [00:58<02:57, 5.91s/it]\n 28%|██▊ | 11/40 [01:04<02:51, 5.91s/it]\n 30%|███ | 12/40 [01:10<02:45, 5.92s/it]\n 32%|███▎ | 13/40 [01:16<02:39, 5.92s/it]\n 35%|███▌ | 14/40 [01:22<02:33, 5.92s/it]\n 38%|███▊ | 15/40 [01:28<02:28, 5.92s/it]\n 40%|████ | 16/40 [01:34<02:22, 5.92s/it]\n 42%|████▎ | 17/40 [01:39<02:16, 5.92s/it]\n 45%|████▌ | 18/40 [01:45<02:10, 5.92s/it]\n 48%|████▊ | 19/40 [01:51<02:04, 5.92s/it]\n 50%|█████ | 20/40 [01:57<01:58, 5.92s/it]\n 52%|█████▎ | 21/40 [02:03<01:52, 5.92s/it]\n 55%|█████▌ | 22/40 [02:09<01:46, 5.92s/it]\n 57%|█████▊ | 23/40 [02:15<01:40, 5.92s/it]\n 60%|██████ | 24/40 [02:21<01:34, 5.92s/it]\n 62%|██████▎ | 25/40 [02:27<01:28, 5.92s/it]\n 65%|██████▌ | 26/40 [02:33<01:22, 5.92s/it]\n 68%|██████▊ | 27/40 [02:39<01:17, 5.92s/it]\n 70%|███████ | 28/40 [02:45<01:11, 5.93s/it]\n 72%|███████▎ | 29/40 [02:51<01:05, 5.92s/it]\n 75%|███████▌ | 30/40 [02:56<00:59, 5.93s/it]\n 78%|███████▊ | 31/40 [03:02<00:53, 5.93s/it]\n 80%|████████ | 32/40 [03:08<00:47, 5.92s/it]\n 82%|████████▎ | 33/40 [03:14<00:41, 5.93s/it]\n 85%|████████▌ | 34/40 [03:20<00:35, 5.92s/it]\n 88%|████████▊ | 35/40 [03:26<00:29, 5.92s/it]\n 90%|█████████ | 36/40 [03:32<00:23, 5.92s/it]\n 92%|█████████▎| 37/40 [03:38<00:17, 5.92s/it]\n 95%|█████████▌| 38/40 [03:44<00:11, 5.92s/it]\n 98%|█████████▊| 39/40 [03:50<00:05, 5.92s/it]\n100%|██████████| 40/40 [03:56<00:00, 5.92s/it]\n100%|██████████| 40/40 [03:56<00:00, 5.90s/it]\nVideo generation completed in 240.27 seconds\nExporting video to: /tmp/tmpbh4k1cz0/output.mp4 at 16 fps\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVideo saved successfully to: /tmp/tmpbh4k1cz0/output.mp4\nCleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Squish/snapshots/70e32c7d833743c88352e2ac973968417fb5b051/squish_18.safetensors", "metrics": { "predict_time": 243.794411078, "total_time": 243.80169 }, "output": "https://replicate.delivery/yhqm/X0yqkQLeLfuNUESVZHL53DIzmRTtkNJiXFOWsZCPDyKamtYUA/output.mp4", "started_at": "2025-03-15T07:05:10.842279Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/yswh-stbbisuimfyka4g75i6zoqbo5sk47km22tmjds2v32vdkwqfiowa", "get": "https://api.replicate.com/v1/predictions/p0xwwxqvpdrj00cnk2fawv6kbr", "cancel": "https://api.replicate.com/v1/predictions/p0xwwxqvpdrj00cnk2fawv6kbr/cancel" }, "version": "f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97" }Generated inStarting prediction with: prompt='In the video, a miniature dog is presented. The dog is held in a person's hands. The person then presses on the dog, causing a sq41sh squish effect. The person keeps pressing down on the dog, further showing the sq41sh squish effect.', lora_strength=1.0, duration=3.0s Calculated 49 frames for 3.0s at 16 fps Loading input image from: /tmp/tmpl6fn4nyqdog-1024.png Image loaded successfully: 1001x991 Auto-selected fixed square dimensions: 512x512 for aspect ratio 0.99 Final dimensions: 512x512 Downloading LoRA from: https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors Downloading from HuggingFace: repo_id=Remade-AI/Squish, filename=squish_18.safetensors Loading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Squish/snapshots/70e32c7d833743c88352e2ac973968417fb5b051/squish_18.safetensors with strength: 1.0 LoRA weights loaded successfully Starting video generation: 49 frames, 40 steps, guidance=5.0 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:05<03:48, 5.87s/it] 5%|▌ | 2/40 [00:11<03:31, 5.55s/it] 8%|▊ | 3/40 [00:17<03:31, 5.71s/it] 10%|█ | 4/40 [00:22<03:28, 5.78s/it] 12%|█▎ | 5/40 [00:28<03:23, 5.82s/it] 15%|█▌ | 6/40 [00:34<03:19, 5.85s/it] 18%|█▊ | 7/40 [00:40<03:13, 5.87s/it] 20%|██ | 8/40 [00:46<03:08, 5.89s/it] 22%|██▎ | 9/40 [00:52<03:02, 5.90s/it] 25%|██▌ | 10/40 [00:58<02:57, 5.91s/it] 28%|██▊ | 11/40 [01:04<02:51, 5.91s/it] 30%|███ | 12/40 [01:10<02:45, 5.92s/it] 32%|███▎ | 13/40 [01:16<02:39, 5.92s/it] 35%|███▌ | 14/40 [01:22<02:33, 5.92s/it] 38%|███▊ | 15/40 [01:28<02:28, 5.92s/it] 40%|████ | 16/40 [01:34<02:22, 5.92s/it] 42%|████▎ | 17/40 [01:39<02:16, 5.92s/it] 45%|████▌ | 18/40 [01:45<02:10, 5.92s/it] 48%|████▊ | 19/40 [01:51<02:04, 5.92s/it] 50%|█████ | 20/40 [01:57<01:58, 5.92s/it] 52%|█████▎ | 21/40 [02:03<01:52, 5.92s/it] 55%|█████▌ | 22/40 [02:09<01:46, 5.92s/it] 57%|█████▊ | 23/40 [02:15<01:40, 5.92s/it] 60%|██████ | 24/40 [02:21<01:34, 5.92s/it] 62%|██████▎ | 25/40 [02:27<01:28, 5.92s/it] 65%|██████▌ | 26/40 [02:33<01:22, 5.92s/it] 68%|██████▊ | 27/40 [02:39<01:17, 5.92s/it] 70%|███████ | 28/40 [02:45<01:11, 5.93s/it] 72%|███████▎ | 29/40 [02:51<01:05, 5.92s/it] 75%|███████▌ | 30/40 [02:56<00:59, 5.93s/it] 78%|███████▊ | 31/40 [03:02<00:53, 5.93s/it] 80%|████████ | 32/40 [03:08<00:47, 5.92s/it] 82%|████████▎ | 33/40 [03:14<00:41, 5.93s/it] 85%|████████▌ | 34/40 [03:20<00:35, 5.92s/it] 88%|████████▊ | 35/40 [03:26<00:29, 5.92s/it] 90%|█████████ | 36/40 [03:32<00:23, 5.92s/it] 92%|█████████▎| 37/40 [03:38<00:17, 5.92s/it] 95%|█████████▌| 38/40 [03:44<00:11, 5.92s/it] 98%|█████████▊| 39/40 [03:50<00:05, 5.92s/it] 100%|██████████| 40/40 [03:56<00:00, 5.92s/it] 100%|██████████| 40/40 [03:56<00:00, 5.90s/it] Video generation completed in 240.27 seconds Exporting video to: /tmp/tmpbh4k1cz0/output.mp4 at 16 fps huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Video saved successfully to: /tmp/tmpbh4k1cz0/output.mp4 Cleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Squish/snapshots/70e32c7d833743c88352e2ac973968417fb5b051/squish_18.safetensorsPrediction
lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97IDem2yb0xnxhrj60cnk2kt0phcacStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedInput
- fps
- 16
- image
- prompt
- In the video, a miniature person is presented. The person is held in a person's hands. The person then presses on the person, causing a sq41sh squish effect. The person keeps pressing down on the person, further showing the sq41sh squish effect.
- duration
- 3
- lora_url
- https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors
- resize_mode
- auto
- lora_strength
- 1
- guidance_scale
- 5
- negative_prompt
- low quality, bad quality, blurry, pixelated, watermark
- num_inference_steps
- 40
{ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf81bFnvCvqeImi1ihBeFfZxBbbKsmT4IZzgghycwXPcq5mO/replicate-prediction-a9acqmz99drme0cnk2crsg2v7g.webp", "prompt": "In the video, a miniature person is presented. The person is held in a person's hands. The person then presses on the person, causing a sq41sh squish effect. The person keeps pressing down on the person, further showing the sq41sh squish effect.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport 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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", { input: { fps: 16, image: "https://replicate.delivery/pbxt/Mf81bFnvCvqeImi1ihBeFfZxBbbKsmT4IZzgghycwXPcq5mO/replicate-prediction-a9acqmz99drme0cnk2crsg2v7g.webp", prompt: "In the video, a miniature person is presented. The person is held in a person's hands. The person then presses on the person, causing a sq41sh squish effect. The person keeps pressing down on the person, further showing the sq41sh squish effect.", duration: 3, lora_url: "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", resize_mode: "auto", lora_strength: 1, guidance_scale: 5, negative_prompt: "low quality, bad quality, blurry, pixelated, watermark", num_inference_steps: 40 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", input={ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf81bFnvCvqeImi1ihBeFfZxBbbKsmT4IZzgghycwXPcq5mO/replicate-prediction-a9acqmz99drme0cnk2crsg2v7g.webp", "prompt": "In the video, a miniature person is presented. The person is held in a person's hands. The person then presses on the person, causing a sq41sh squish effect. The person keeps pressing down on the person, further showing the sq41sh squish effect.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/wan2.1-i2v-lora 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": "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf81bFnvCvqeImi1ihBeFfZxBbbKsmT4IZzgghycwXPcq5mO/replicate-prediction-a9acqmz99drme0cnk2crsg2v7g.webp", "prompt": "In the video, a miniature person is presented. The person is held in a person\'s hands. The person then presses on the person, causing a sq41sh squish effect. The person keeps pressing down on the person, further showing the sq41sh squish effect.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-03-15T07:18:50.056075Z", "created_at": "2025-03-15T07:14:42.796000Z", "data_removed": false, "error": null, "id": "em2yb0xnxhrj60cnk2kt0phcac", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf81bFnvCvqeImi1ihBeFfZxBbbKsmT4IZzgghycwXPcq5mO/replicate-prediction-a9acqmz99drme0cnk2crsg2v7g.webp", "prompt": "In the video, a miniature person is presented. The person is held in a person's hands. The person then presses on the person, causing a sq41sh squish effect. The person keeps pressing down on the person, further showing the sq41sh squish effect.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }, "logs": "Starting prediction with: prompt='In the video, a miniature person is presented. The person is held in a person's hands. The person then presses on the person, causing a sq41sh squish effect. The person keeps pressing down on the person, further showing the sq41sh squish effect.', lora_strength=1.0, duration=3.0s\nCalculated 49 frames for 3.0s at 16 fps\nLoading input image from: /tmp/tmp4rnjybzareplicate-prediction-a9acqmz99drme0cnk2crsg2v7g.webp\nImage loaded successfully: 1024x1024\nAuto-selected fixed square dimensions: 512x512 for aspect ratio 1.00\nFinal dimensions: 512x512\nDownloading LoRA from: https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors\nDownloading from HuggingFace: repo_id=Remade-AI/Squish, filename=squish_18.safetensors\nLoading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Squish/snapshots/70e32c7d833743c88352e2ac973968417fb5b051/squish_18.safetensors with strength: 1.0\nLoRA weights loaded successfully\nStarting video generation: 49 frames, 40 steps, guidance=5.0\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:06<03:54, 6.01s/it]\n 5%|▌ | 2/40 [00:11<03:36, 5.69s/it]\n 8%|▊ | 3/40 [00:17<03:36, 5.85s/it]\n 10%|█ | 4/40 [00:23<03:33, 5.92s/it]\n 12%|█▎ | 5/40 [00:29<03:28, 5.96s/it]\n 15%|█▌ | 6/40 [00:35<03:23, 5.99s/it]\n 18%|█▊ | 7/40 [00:41<03:18, 6.01s/it]\n 20%|██ | 8/40 [00:47<03:12, 6.02s/it]\n 22%|██▎ | 9/40 [00:53<03:06, 6.03s/it]\n 25%|██▌ | 10/40 [00:59<03:01, 6.04s/it]\n 28%|██▊ | 11/40 [01:05<02:55, 6.04s/it]\n 30%|███ | 12/40 [01:11<02:49, 6.04s/it]\n 32%|███▎ | 13/40 [01:17<02:43, 6.05s/it]\n 35%|███▌ | 14/40 [01:24<02:37, 6.05s/it]\n 38%|███▊ | 15/40 [01:30<02:31, 6.05s/it]\n 40%|████ | 16/40 [01:36<02:25, 6.05s/it]\n 42%|████▎ | 17/40 [01:42<02:19, 6.05s/it]\n 45%|████▌ | 18/40 [01:48<02:13, 6.05s/it]\n 48%|████▊ | 19/40 [01:54<02:07, 6.05s/it]\n 50%|█████ | 20/40 [02:00<02:01, 6.05s/it]\n 52%|█████▎ | 21/40 [02:06<01:54, 6.05s/it]\n 55%|█████▌ | 22/40 [02:12<01:48, 6.05s/it]\n 57%|█████▊ | 23/40 [02:18<01:42, 6.05s/it]\n 60%|██████ | 24/40 [02:24<01:36, 6.05s/it]\n 62%|██████▎ | 25/40 [02:30<01:30, 6.05s/it]\n 65%|██████▌ | 26/40 [02:36<01:24, 6.05s/it]\n 68%|██████▊ | 27/40 [02:42<01:18, 6.05s/it]\n 70%|███████ | 28/40 [02:48<01:12, 6.05s/it]\n 72%|███████▎ | 29/40 [02:54<01:06, 6.05s/it]\n 75%|███████▌ | 30/40 [03:00<01:00, 6.05s/it]\n 78%|███████▊ | 31/40 [03:06<00:54, 6.05s/it]\n 80%|████████ | 32/40 [03:12<00:48, 6.05s/it]\n 82%|████████▎ | 33/40 [03:18<00:42, 6.05s/it]\n 85%|████████▌ | 34/40 [03:25<00:36, 6.05s/it]\n 88%|████████▊ | 35/40 [03:31<00:30, 6.05s/it]\n 90%|█████████ | 36/40 [03:37<00:24, 6.05s/it]\n 92%|█████████▎| 37/40 [03:43<00:18, 6.05s/it]\n 95%|█████████▌| 38/40 [03:49<00:12, 6.05s/it]\n 98%|█████████▊| 39/40 [03:55<00:06, 6.05s/it]\n100%|██████████| 40/40 [04:01<00:00, 6.04s/it]\n100%|██████████| 40/40 [04:01<00:00, 6.03s/it]\nVideo generation completed in 245.46 seconds\nExporting video to: /tmp/tmprsdegzeg/output.mp4 at 16 fps\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVideo saved successfully to: /tmp/tmprsdegzeg/output.mp4\nCleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Squish/snapshots/70e32c7d833743c88352e2ac973968417fb5b051/squish_18.safetensors", "metrics": { "predict_time": 247.249060088, "total_time": 247.260075 }, "output": "https://replicate.delivery/yhqm/kFaFq76JLjrLNtUgVsxZoPpOgD9mzDbga7qBzBWh9eTt3WMKA/output.mp4", "started_at": "2025-03-15T07:14:42.807015Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/yswh-g55om235ootazqpgltis3pp6ir64odxsfijqsv4rzyfiacqxyviq", "get": "https://api.replicate.com/v1/predictions/em2yb0xnxhrj60cnk2kt0phcac", "cancel": "https://api.replicate.com/v1/predictions/em2yb0xnxhrj60cnk2kt0phcac/cancel" }, "version": "f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97" }Generated inStarting prediction with: prompt='In the video, a miniature person is presented. The person is held in a person's hands. The person then presses on the person, causing a sq41sh squish effect. The person keeps pressing down on the person, further showing the sq41sh squish effect.', lora_strength=1.0, duration=3.0s Calculated 49 frames for 3.0s at 16 fps Loading input image from: /tmp/tmp4rnjybzareplicate-prediction-a9acqmz99drme0cnk2crsg2v7g.webp Image loaded successfully: 1024x1024 Auto-selected fixed square dimensions: 512x512 for aspect ratio 1.00 Final dimensions: 512x512 Downloading LoRA from: https://huggingface.co/Remade-AI/Squish/resolve/main/squish_18.safetensors Downloading from HuggingFace: repo_id=Remade-AI/Squish, filename=squish_18.safetensors Loading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Squish/snapshots/70e32c7d833743c88352e2ac973968417fb5b051/squish_18.safetensors with strength: 1.0 LoRA weights loaded successfully Starting video generation: 49 frames, 40 steps, guidance=5.0 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:06<03:54, 6.01s/it] 5%|▌ | 2/40 [00:11<03:36, 5.69s/it] 8%|▊ | 3/40 [00:17<03:36, 5.85s/it] 10%|█ | 4/40 [00:23<03:33, 5.92s/it] 12%|█▎ | 5/40 [00:29<03:28, 5.96s/it] 15%|█▌ | 6/40 [00:35<03:23, 5.99s/it] 18%|█▊ | 7/40 [00:41<03:18, 6.01s/it] 20%|██ | 8/40 [00:47<03:12, 6.02s/it] 22%|██▎ | 9/40 [00:53<03:06, 6.03s/it] 25%|██▌ | 10/40 [00:59<03:01, 6.04s/it] 28%|██▊ | 11/40 [01:05<02:55, 6.04s/it] 30%|███ | 12/40 [01:11<02:49, 6.04s/it] 32%|███▎ | 13/40 [01:17<02:43, 6.05s/it] 35%|███▌ | 14/40 [01:24<02:37, 6.05s/it] 38%|███▊ | 15/40 [01:30<02:31, 6.05s/it] 40%|████ | 16/40 [01:36<02:25, 6.05s/it] 42%|████▎ | 17/40 [01:42<02:19, 6.05s/it] 45%|████▌ | 18/40 [01:48<02:13, 6.05s/it] 48%|████▊ | 19/40 [01:54<02:07, 6.05s/it] 50%|█████ | 20/40 [02:00<02:01, 6.05s/it] 52%|█████▎ | 21/40 [02:06<01:54, 6.05s/it] 55%|█████▌ | 22/40 [02:12<01:48, 6.05s/it] 57%|█████▊ | 23/40 [02:18<01:42, 6.05s/it] 60%|██████ | 24/40 [02:24<01:36, 6.05s/it] 62%|██████▎ | 25/40 [02:30<01:30, 6.05s/it] 65%|██████▌ | 26/40 [02:36<01:24, 6.05s/it] 68%|██████▊ | 27/40 [02:42<01:18, 6.05s/it] 70%|███████ | 28/40 [02:48<01:12, 6.05s/it] 72%|███████▎ | 29/40 [02:54<01:06, 6.05s/it] 75%|███████▌ | 30/40 [03:00<01:00, 6.05s/it] 78%|███████▊ | 31/40 [03:06<00:54, 6.05s/it] 80%|████████ | 32/40 [03:12<00:48, 6.05s/it] 82%|████████▎ | 33/40 [03:18<00:42, 6.05s/it] 85%|████████▌ | 34/40 [03:25<00:36, 6.05s/it] 88%|████████▊ | 35/40 [03:31<00:30, 6.05s/it] 90%|█████████ | 36/40 [03:37<00:24, 6.05s/it] 92%|█████████▎| 37/40 [03:43<00:18, 6.05s/it] 95%|█████████▌| 38/40 [03:49<00:12, 6.05s/it] 98%|█████████▊| 39/40 [03:55<00:06, 6.05s/it] 100%|██████████| 40/40 [04:01<00:00, 6.04s/it] 100%|██████████| 40/40 [04:01<00:00, 6.03s/it] Video generation completed in 245.46 seconds Exporting video to: /tmp/tmprsdegzeg/output.mp4 at 16 fps huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Video saved successfully to: /tmp/tmprsdegzeg/output.mp4 Cleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Squish/snapshots/70e32c7d833743c88352e2ac973968417fb5b051/squish_18.safetensorsPrediction
lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97ID1rj0rey34drj00cnk2n94xz4s4StatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedby @lucatacoInput
- fps
- 16
- image
- prompt
- The banana sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.
- duration
- 3
- lora_url
- https://huggingface.co/Remade-AI/Inflate/resolve/main/inflate_20_epochs.safetensors
- resize_mode
- auto
- lora_strength
- 1
- guidance_scale
- 5
- negative_prompt
- low quality, bad quality, blurry, pixelated, watermark
- num_inference_steps
- 40
{ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf84kmeE1R1lv9Xvg34TEVN6MlcB1lL6XgXOuoC9Z2B6k5Vb/replicate-prediction-a4g8h6w4w9rm80cnk2kr42z5dc.jpg", "prompt": "The banana sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Inflate/resolve/main/inflate_20_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport 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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", { input: { fps: 16, image: "https://replicate.delivery/pbxt/Mf84kmeE1R1lv9Xvg34TEVN6MlcB1lL6XgXOuoC9Z2B6k5Vb/replicate-prediction-a4g8h6w4w9rm80cnk2kr42z5dc.jpg", prompt: "The banana sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.", duration: 3, lora_url: "https://huggingface.co/Remade-AI/Inflate/resolve/main/inflate_20_epochs.safetensors", resize_mode: "auto", lora_strength: 1, guidance_scale: 5, negative_prompt: "low quality, bad quality, blurry, pixelated, watermark", num_inference_steps: 40 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", input={ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf84kmeE1R1lv9Xvg34TEVN6MlcB1lL6XgXOuoC9Z2B6k5Vb/replicate-prediction-a4g8h6w4w9rm80cnk2kr42z5dc.jpg", "prompt": "The banana sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Inflate/resolve/main/inflate_20_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/wan2.1-i2v-lora 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": "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf84kmeE1R1lv9Xvg34TEVN6MlcB1lL6XgXOuoC9Z2B6k5Vb/replicate-prediction-a4g8h6w4w9rm80cnk2kr42z5dc.jpg", "prompt": "The banana sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Inflate/resolve/main/inflate_20_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-03-15T07:22:59.435227Z", "created_at": "2025-03-15T07:18:02.787000Z", "data_removed": false, "error": null, "id": "1rj0rey34drj00cnk2n94xz4s4", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf84kmeE1R1lv9Xvg34TEVN6MlcB1lL6XgXOuoC9Z2B6k5Vb/replicate-prediction-a4g8h6w4w9rm80cnk2kr42z5dc.jpg", "prompt": "The banana sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Inflate/resolve/main/inflate_20_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }, "logs": "Starting prediction with: prompt='The banana sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.', lora_strength=1.0, duration=3.0s\nCalculated 49 frames for 3.0s at 16 fps\nLoading input image from: /tmp/tmp64qav38areplicate-prediction-a4g8h6w4w9rm80cnk2kr42z5dc.jpg\nImage loaded successfully: 1024x1024\nAuto-selected fixed square dimensions: 512x512 for aspect ratio 1.00\nFinal dimensions: 512x512\nDownloading LoRA from: https://huggingface.co/Remade-AI/Inflate/resolve/main/inflate_20_epochs.safetensors\nDownloading from HuggingFace: repo_id=Remade-AI/Inflate, filename=inflate_20_epochs.safetensors\nLoading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Inflate/snapshots/76242908d91d69292a85c19bf8575e898732608e/inflate_20_epochs.safetensors with strength: 1.0\nLoRA weights loaded successfully\nStarting video generation: 49 frames, 40 steps, guidance=5.0\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:06<03:55, 6.04s/it]\n 5%|▌ | 2/40 [00:11<03:37, 5.72s/it]\n 8%|▊ | 3/40 [00:17<03:37, 5.87s/it]\n 10%|█ | 4/40 [00:23<03:33, 5.94s/it]\n 12%|█▎ | 5/40 [00:29<03:29, 5.98s/it]\n 15%|█▌ | 6/40 [00:35<03:24, 6.00s/it]\n 18%|█▊ | 7/40 [00:41<03:18, 6.02s/it]\n 20%|██ | 8/40 [00:47<03:12, 6.03s/it]\n 22%|██▎ | 9/40 [00:53<03:07, 6.04s/it]\n 25%|██▌ | 10/40 [00:59<03:01, 6.04s/it]\n 28%|██▊ | 11/40 [01:05<02:55, 6.04s/it]\n 30%|███ | 12/40 [01:12<02:49, 6.05s/it]\n 32%|███▎ | 13/40 [01:18<02:43, 6.05s/it]\n 35%|███▌ | 14/40 [01:24<02:37, 6.05s/it]\n 38%|███▊ | 15/40 [01:30<02:31, 6.05s/it]\n 40%|████ | 16/40 [01:36<02:25, 6.05s/it]\n 42%|████▎ | 17/40 [01:42<02:19, 6.05s/it]\n 45%|████▌ | 18/40 [01:48<02:13, 6.05s/it]\n 48%|████▊ | 19/40 [01:54<02:07, 6.05s/it]\n 50%|█████ | 20/40 [02:00<02:00, 6.05s/it]\n 52%|█████▎ | 21/40 [02:06<01:54, 6.05s/it]\n 55%|█████▌ | 22/40 [02:12<01:48, 6.05s/it]\n 57%|█████▊ | 23/40 [02:18<01:42, 6.05s/it]\n 60%|██████ | 24/40 [02:24<01:36, 6.05s/it]\n 62%|██████▎ | 25/40 [02:30<01:30, 6.05s/it]\n 65%|██████▌ | 26/40 [02:36<01:24, 6.05s/it]\n 68%|██████▊ | 27/40 [02:42<01:18, 6.05s/it]\n 70%|███████ | 28/40 [02:48<01:12, 6.05s/it]\n 72%|███████▎ | 29/40 [02:54<01:06, 6.05s/it]\n 75%|███████▌ | 30/40 [03:00<01:00, 6.05s/it]\n 78%|███████▊ | 31/40 [03:06<00:54, 6.05s/it]\n 80%|████████ | 32/40 [03:13<00:48, 6.05s/it]\n 82%|████████▎ | 33/40 [03:19<00:42, 6.05s/it]\n 85%|████████▌ | 34/40 [03:25<00:36, 6.04s/it]\n 88%|████████▊ | 35/40 [03:31<00:30, 6.04s/it]\n 90%|█████████ | 36/40 [03:37<00:24, 6.04s/it]\n 92%|█████████▎| 37/40 [03:43<00:18, 6.04s/it]\n 95%|█████████▌| 38/40 [03:49<00:12, 6.04s/it]\n 98%|█████████▊| 39/40 [03:55<00:06, 6.04s/it]\n100%|██████████| 40/40 [04:01<00:00, 6.04s/it]\n100%|██████████| 40/40 [04:01<00:00, 6.03s/it]\nVideo generation completed in 245.50 seconds\nExporting video to: /tmp/tmp8_g5bim4/output.mp4 at 16 fps\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVideo saved successfully to: /tmp/tmp8_g5bim4/output.mp4\nCleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Inflate/snapshots/76242908d91d69292a85c19bf8575e898732608e/inflate_20_epochs.safetensors", "metrics": { "predict_time": 249.178444969, "total_time": 296.648227 }, "output": "https://replicate.delivery/yhqm/It7Q2f0fBZpi5EyUkdYYOrIZBqcgDsj212XfvozXcp8nmbxoA/output.mp4", "started_at": "2025-03-15T07:18:50.256782Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/yswh-hcmwy76opzwrhp3lrzmkumqbw5q6hn3ktjs7i3hqhwqofwn5kv5q", "get": "https://api.replicate.com/v1/predictions/1rj0rey34drj00cnk2n94xz4s4", "cancel": "https://api.replicate.com/v1/predictions/1rj0rey34drj00cnk2n94xz4s4/cancel" }, "version": "f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97" }Generated inStarting prediction with: prompt='The banana sits on a light gray surface, then infl4t3 inflates it, its skin becoming taut and glossy as it transforms into a perfect, inflated sphere.', lora_strength=1.0, duration=3.0s Calculated 49 frames for 3.0s at 16 fps Loading input image from: /tmp/tmp64qav38areplicate-prediction-a4g8h6w4w9rm80cnk2kr42z5dc.jpg Image loaded successfully: 1024x1024 Auto-selected fixed square dimensions: 512x512 for aspect ratio 1.00 Final dimensions: 512x512 Downloading LoRA from: https://huggingface.co/Remade-AI/Inflate/resolve/main/inflate_20_epochs.safetensors Downloading from HuggingFace: repo_id=Remade-AI/Inflate, filename=inflate_20_epochs.safetensors Loading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Inflate/snapshots/76242908d91d69292a85c19bf8575e898732608e/inflate_20_epochs.safetensors with strength: 1.0 LoRA weights loaded successfully Starting video generation: 49 frames, 40 steps, guidance=5.0 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:06<03:55, 6.04s/it] 5%|▌ | 2/40 [00:11<03:37, 5.72s/it] 8%|▊ | 3/40 [00:17<03:37, 5.87s/it] 10%|█ | 4/40 [00:23<03:33, 5.94s/it] 12%|█▎ | 5/40 [00:29<03:29, 5.98s/it] 15%|█▌ | 6/40 [00:35<03:24, 6.00s/it] 18%|█▊ | 7/40 [00:41<03:18, 6.02s/it] 20%|██ | 8/40 [00:47<03:12, 6.03s/it] 22%|██▎ | 9/40 [00:53<03:07, 6.04s/it] 25%|██▌ | 10/40 [00:59<03:01, 6.04s/it] 28%|██▊ | 11/40 [01:05<02:55, 6.04s/it] 30%|███ | 12/40 [01:12<02:49, 6.05s/it] 32%|███▎ | 13/40 [01:18<02:43, 6.05s/it] 35%|███▌ | 14/40 [01:24<02:37, 6.05s/it] 38%|███▊ | 15/40 [01:30<02:31, 6.05s/it] 40%|████ | 16/40 [01:36<02:25, 6.05s/it] 42%|████▎ | 17/40 [01:42<02:19, 6.05s/it] 45%|████▌ | 18/40 [01:48<02:13, 6.05s/it] 48%|████▊ | 19/40 [01:54<02:07, 6.05s/it] 50%|█████ | 20/40 [02:00<02:00, 6.05s/it] 52%|█████▎ | 21/40 [02:06<01:54, 6.05s/it] 55%|█████▌ | 22/40 [02:12<01:48, 6.05s/it] 57%|█████▊ | 23/40 [02:18<01:42, 6.05s/it] 60%|██████ | 24/40 [02:24<01:36, 6.05s/it] 62%|██████▎ | 25/40 [02:30<01:30, 6.05s/it] 65%|██████▌ | 26/40 [02:36<01:24, 6.05s/it] 68%|██████▊ | 27/40 [02:42<01:18, 6.05s/it] 70%|███████ | 28/40 [02:48<01:12, 6.05s/it] 72%|███████▎ | 29/40 [02:54<01:06, 6.05s/it] 75%|███████▌ | 30/40 [03:00<01:00, 6.05s/it] 78%|███████▊ | 31/40 [03:06<00:54, 6.05s/it] 80%|████████ | 32/40 [03:13<00:48, 6.05s/it] 82%|████████▎ | 33/40 [03:19<00:42, 6.05s/it] 85%|████████▌ | 34/40 [03:25<00:36, 6.04s/it] 88%|████████▊ | 35/40 [03:31<00:30, 6.04s/it] 90%|█████████ | 36/40 [03:37<00:24, 6.04s/it] 92%|█████████▎| 37/40 [03:43<00:18, 6.04s/it] 95%|█████████▌| 38/40 [03:49<00:12, 6.04s/it] 98%|█████████▊| 39/40 [03:55<00:06, 6.04s/it] 100%|██████████| 40/40 [04:01<00:00, 6.04s/it] 100%|██████████| 40/40 [04:01<00:00, 6.03s/it] Video generation completed in 245.50 seconds Exporting video to: /tmp/tmp8_g5bim4/output.mp4 at 16 fps huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Video saved successfully to: /tmp/tmp8_g5bim4/output.mp4 Cleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Inflate/snapshots/76242908d91d69292a85c19bf8575e898732608e/inflate_20_epochs.safetensorsPrediction
lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97ID1000xcx41xrj20cnk2pvwnqv8mStatusSucceededSourceWebHardwareA100 (80GB)Total durationCreatedby @lucatacoInput
- fps
- 16
- image
- prompt
- The video opens on a hat. A knife, held by a hand, is coming into frame and hovering over the hat. The knife then begins cutting into the hat to c4k3 cakeify it. As the knife slices the hat open, the inside of the hat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the hat are revealed.
- duration
- 3
- lora_url
- https://huggingface.co/Remade-AI/Cakeify/resolve/main/cakeify_16_epochs.safetensors
- resize_mode
- auto
- lora_strength
- 1
- guidance_scale
- 5
- negative_prompt
- low quality, bad quality, blurry, pixelated, watermark
- num_inference_steps
- 40
{ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf87jEsBiOD55AXmLBCJ0l6vGbY9rvdryY2DgfJcDatpNSs2/replicate-prediction-msxxscfrexrma0cn7sp8z9kjbg%20%281%29.png", "prompt": "The video opens on a hat. A knife, held by a hand, is coming into frame and hovering over the hat. The knife then begins cutting into the hat to c4k3 cakeify it. As the knife slices the hat open, the inside of the hat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the hat are revealed.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Cakeify/resolve/main/cakeify_16_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }Install Replicate’s Node.js client library:npm install replicateImport 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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", { input: { fps: 16, image: "https://replicate.delivery/pbxt/Mf87jEsBiOD55AXmLBCJ0l6vGbY9rvdryY2DgfJcDatpNSs2/replicate-prediction-msxxscfrexrma0cn7sp8z9kjbg%20%281%29.png", prompt: "The video opens on a hat. A knife, held by a hand, is coming into frame and hovering over the hat. The knife then begins cutting into the hat to c4k3 cakeify it. As the knife slices the hat open, the inside of the hat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the hat are revealed.", duration: 3, lora_url: "https://huggingface.co/Remade-AI/Cakeify/resolve/main/cakeify_16_epochs.safetensors", resize_mode: "auto", lora_strength: 1, guidance_scale: 5, negative_prompt: "low quality, bad quality, blurry, pixelated, watermark", num_inference_steps: 40 } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);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 lucataco/wan2.1-i2v-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", input={ "fps": 16, "image": "https://replicate.delivery/pbxt/Mf87jEsBiOD55AXmLBCJ0l6vGbY9rvdryY2DgfJcDatpNSs2/replicate-prediction-msxxscfrexrma0cn7sp8z9kjbg%20%281%29.png", "prompt": "The video opens on a hat. A knife, held by a hand, is coming into frame and hovering over the hat. The knife then begins cutting into the hat to c4k3 cakeify it. As the knife slices the hat open, the inside of the hat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the hat are revealed.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Cakeify/resolve/main/cakeify_16_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } ) print(output)To learn more, take a look at the guide on getting started with Python.
Run lucataco/wan2.1-i2v-lora 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": "lucataco/wan2.1-i2v-lora:f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf87jEsBiOD55AXmLBCJ0l6vGbY9rvdryY2DgfJcDatpNSs2/replicate-prediction-msxxscfrexrma0cn7sp8z9kjbg%20%281%29.png", "prompt": "The video opens on a hat. A knife, held by a hand, is coming into frame and hovering over the hat. The knife then begins cutting into the hat to c4k3 cakeify it. As the knife slices the hat open, the inside of the hat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the hat are revealed.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Cakeify/resolve/main/cakeify_16_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 } }' \ https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2025-03-15T07:27:08.199439Z", "created_at": "2025-03-15T07:21:11.439000Z", "data_removed": false, "error": null, "id": "1000xcx41xrj20cnk2pvwnqv8m", "input": { "fps": 16, "image": "https://replicate.delivery/pbxt/Mf87jEsBiOD55AXmLBCJ0l6vGbY9rvdryY2DgfJcDatpNSs2/replicate-prediction-msxxscfrexrma0cn7sp8z9kjbg%20%281%29.png", "prompt": "The video opens on a hat. A knife, held by a hand, is coming into frame and hovering over the hat. The knife then begins cutting into the hat to c4k3 cakeify it. As the knife slices the hat open, the inside of the hat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the hat are revealed.", "duration": 3, "lora_url": "https://huggingface.co/Remade-AI/Cakeify/resolve/main/cakeify_16_epochs.safetensors", "resize_mode": "auto", "lora_strength": 1, "guidance_scale": 5, "negative_prompt": "low quality, bad quality, blurry, pixelated, watermark", "num_inference_steps": 40 }, "logs": "Starting prediction with: prompt='The video opens on a hat. A knife, held by a hand, is coming into frame and hovering over the hat. The knife then begins cutting into the hat to c4k3 cakeify it. As the knife slices the hat open, the inside of the hat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the hat are revealed.', lora_strength=1.0, duration=3.0s\nCalculated 49 frames for 3.0s at 16 fps\nLoading input image from: /tmp/tmpa1af0xo1replicate-prediction-msxxscfrexrma0cn7sp8z9kjbg (1).png\nImage loaded successfully: 768x768\nAuto-selected fixed square dimensions: 512x512 for aspect ratio 1.00\nFinal dimensions: 512x512\nDownloading LoRA from: https://huggingface.co/Remade-AI/Cakeify/resolve/main/cakeify_16_epochs.safetensors\nDownloading from HuggingFace: repo_id=Remade-AI/Cakeify, filename=cakeify_16_epochs.safetensors\nLoading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Cakeify/snapshots/0342201ecfb3cf1c06dd22369935d27f25e5f4ca/cakeify_16_epochs.safetensors with strength: 1.0\nLoRA weights loaded successfully\nStarting video generation: 49 frames, 40 steps, guidance=5.0\n 0%| | 0/40 [00:00<?, ?it/s]\n 2%|▎ | 1/40 [00:06<03:55, 6.05s/it]\n 5%|▌ | 2/40 [00:11<03:37, 5.72s/it]\n 8%|▊ | 3/40 [00:17<03:37, 5.88s/it]\n 10%|█ | 4/40 [00:23<03:34, 5.95s/it]\n 12%|█▎ | 5/40 [00:29<03:29, 5.99s/it]\n 15%|█▌ | 6/40 [00:35<03:24, 6.01s/it]\n 18%|█▊ | 7/40 [00:41<03:18, 6.02s/it]\n 20%|██ | 8/40 [00:47<03:13, 6.04s/it]\n 22%|██▎ | 9/40 [00:53<03:07, 6.04s/it]\n 25%|██▌ | 10/40 [00:59<03:01, 6.05s/it]\n 28%|██▊ | 11/40 [01:06<02:55, 6.05s/it]\n 30%|███ | 12/40 [01:12<02:49, 6.05s/it]\n 32%|███▎ | 13/40 [01:18<02:43, 6.05s/it]\n 35%|███▌ | 14/40 [01:24<02:37, 6.05s/it]\n 38%|███▊ | 15/40 [01:30<02:31, 6.05s/it]\n 40%|████ | 16/40 [01:36<02:25, 6.05s/it]\n 42%|████▎ | 17/40 [01:42<02:19, 6.06s/it]\n 45%|████▌ | 18/40 [01:48<02:13, 6.05s/it]\n 48%|████▊ | 19/40 [01:54<02:07, 6.05s/it]\n 50%|█████ | 20/40 [02:00<02:01, 6.06s/it]\n 52%|█████▎ | 21/40 [02:06<01:55, 6.06s/it]\n 55%|█████▌ | 22/40 [02:12<01:49, 6.06s/it]\n 57%|█████▊ | 23/40 [02:18<01:42, 6.06s/it]\n 60%|██████ | 24/40 [02:24<01:36, 6.05s/it]\n 62%|██████▎ | 25/40 [02:30<01:30, 6.05s/it]\n 65%|██████▌ | 26/40 [02:36<01:24, 6.05s/it]\n 68%|██████▊ | 27/40 [02:42<01:18, 6.05s/it]\n 70%|███████ | 28/40 [02:48<01:12, 6.05s/it]\n 72%|███████▎ | 29/40 [02:55<01:06, 6.05s/it]\n 75%|███████▌ | 30/40 [03:01<01:00, 6.05s/it]\n 78%|███████▊ | 31/40 [03:07<00:54, 6.05s/it]\n 80%|████████ | 32/40 [03:13<00:48, 6.05s/it]\n 82%|████████▎ | 33/40 [03:19<00:42, 6.05s/it]\n 85%|████████▌ | 34/40 [03:25<00:36, 6.05s/it]\n 88%|████████▊ | 35/40 [03:31<00:30, 6.05s/it]\n 90%|█████████ | 36/40 [03:37<00:24, 6.05s/it]\n 92%|█████████▎| 37/40 [03:43<00:18, 6.05s/it]\n 95%|█████████▌| 38/40 [03:49<00:12, 6.05s/it]\n 98%|█████████▊| 39/40 [03:55<00:06, 6.05s/it]\n100%|██████████| 40/40 [04:01<00:00, 6.05s/it]\n100%|██████████| 40/40 [04:01<00:00, 6.04s/it]\nVideo generation completed in 245.76 seconds\nExporting video to: /tmp/tmp81b7n0cw/output.mp4 at 16 fps\nhuggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\nTo disable this warning, you can either:\n- Avoid using `tokenizers` before the fork if possible\n- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\nVideo saved successfully to: /tmp/tmp81b7n0cw/output.mp4\nCleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Cakeify/snapshots/0342201ecfb3cf1c06dd22369935d27f25e5f4ca/cakeify_16_epochs.safetensors", "metrics": { "predict_time": 248.581746119, "total_time": 356.760439 }, "output": "https://replicate.delivery/yhqm/6BgcVmXtMC7jCRMAGf7JwUU2k8vHhRsSL5ZYXG7Ng4Im7WMKA/output.mp4", "started_at": "2025-03-15T07:22:59.617693Z", "status": "succeeded", "urls": { "stream": "https://stream.replicate.com/v1/files/yswh-hxxond6673e7kmjpoczfo5tjjq3c3gmogxfzlzbfe732ihuwo63a", "get": "https://api.replicate.com/v1/predictions/1000xcx41xrj20cnk2pvwnqv8m", "cancel": "https://api.replicate.com/v1/predictions/1000xcx41xrj20cnk2pvwnqv8m/cancel" }, "version": "f130c663a974802a8e5826a49b82064a27d5ffeec8f008ae3195a70e49527a97" }Generated inStarting prediction with: prompt='The video opens on a hat. A knife, held by a hand, is coming into frame and hovering over the hat. The knife then begins cutting into the hat to c4k3 cakeify it. As the knife slices the hat open, the inside of the hat is revealed to be cake with chocolate layers. The knife cuts through and the contents of the hat are revealed.', lora_strength=1.0, duration=3.0s Calculated 49 frames for 3.0s at 16 fps Loading input image from: /tmp/tmpa1af0xo1replicate-prediction-msxxscfrexrma0cn7sp8z9kjbg (1).png Image loaded successfully: 768x768 Auto-selected fixed square dimensions: 512x512 for aspect ratio 1.00 Final dimensions: 512x512 Downloading LoRA from: https://huggingface.co/Remade-AI/Cakeify/resolve/main/cakeify_16_epochs.safetensors Downloading from HuggingFace: repo_id=Remade-AI/Cakeify, filename=cakeify_16_epochs.safetensors Loading LoRA weights from: /root/.cache/huggingface/hub/models--Remade-AI--Cakeify/snapshots/0342201ecfb3cf1c06dd22369935d27f25e5f4ca/cakeify_16_epochs.safetensors with strength: 1.0 LoRA weights loaded successfully Starting video generation: 49 frames, 40 steps, guidance=5.0 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:06<03:55, 6.05s/it] 5%|▌ | 2/40 [00:11<03:37, 5.72s/it] 8%|▊ | 3/40 [00:17<03:37, 5.88s/it] 10%|█ | 4/40 [00:23<03:34, 5.95s/it] 12%|█▎ | 5/40 [00:29<03:29, 5.99s/it] 15%|█▌ | 6/40 [00:35<03:24, 6.01s/it] 18%|█▊ | 7/40 [00:41<03:18, 6.02s/it] 20%|██ | 8/40 [00:47<03:13, 6.04s/it] 22%|██▎ | 9/40 [00:53<03:07, 6.04s/it] 25%|██▌ | 10/40 [00:59<03:01, 6.05s/it] 28%|██▊ | 11/40 [01:06<02:55, 6.05s/it] 30%|███ | 12/40 [01:12<02:49, 6.05s/it] 32%|███▎ | 13/40 [01:18<02:43, 6.05s/it] 35%|███▌ | 14/40 [01:24<02:37, 6.05s/it] 38%|███▊ | 15/40 [01:30<02:31, 6.05s/it] 40%|████ | 16/40 [01:36<02:25, 6.05s/it] 42%|████▎ | 17/40 [01:42<02:19, 6.06s/it] 45%|████▌ | 18/40 [01:48<02:13, 6.05s/it] 48%|████▊ | 19/40 [01:54<02:07, 6.05s/it] 50%|█████ | 20/40 [02:00<02:01, 6.06s/it] 52%|█████▎ | 21/40 [02:06<01:55, 6.06s/it] 55%|█████▌ | 22/40 [02:12<01:49, 6.06s/it] 57%|█████▊ | 23/40 [02:18<01:42, 6.06s/it] 60%|██████ | 24/40 [02:24<01:36, 6.05s/it] 62%|██████▎ | 25/40 [02:30<01:30, 6.05s/it] 65%|██████▌ | 26/40 [02:36<01:24, 6.05s/it] 68%|██████▊ | 27/40 [02:42<01:18, 6.05s/it] 70%|███████ | 28/40 [02:48<01:12, 6.05s/it] 72%|███████▎ | 29/40 [02:55<01:06, 6.05s/it] 75%|███████▌ | 30/40 [03:01<01:00, 6.05s/it] 78%|███████▊ | 31/40 [03:07<00:54, 6.05s/it] 80%|████████ | 32/40 [03:13<00:48, 6.05s/it] 82%|████████▎ | 33/40 [03:19<00:42, 6.05s/it] 85%|████████▌ | 34/40 [03:25<00:36, 6.05s/it] 88%|████████▊ | 35/40 [03:31<00:30, 6.05s/it] 90%|█████████ | 36/40 [03:37<00:24, 6.05s/it] 92%|█████████▎| 37/40 [03:43<00:18, 6.05s/it] 95%|█████████▌| 38/40 [03:49<00:12, 6.05s/it] 98%|█████████▊| 39/40 [03:55<00:06, 6.05s/it] 100%|██████████| 40/40 [04:01<00:00, 6.05s/it] 100%|██████████| 40/40 [04:01<00:00, 6.04s/it] Video generation completed in 245.76 seconds Exporting video to: /tmp/tmp81b7n0cw/output.mp4 at 16 fps huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) Video saved successfully to: /tmp/tmp81b7n0cw/output.mp4 Cleaned up temporary LoRA file: /root/.cache/huggingface/hub/models--Remade-AI--Cakeify/snapshots/0342201ecfb3cf1c06dd22369935d27f25e5f4ca/cakeify_16_epochs.safetensors
Want to make some of these yourself?
Run this model
