zsxkib/animate-diff 🔢📝❓ → 🖼️
About
🎨 AnimateDiff (w/ MotionLoRAs for Panning, Zooming, etc): Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

Example Output
Prompt:
"a medium shot of a vibrant coral reef with a variety of marine life, rainbow, visual effects, prores, cineon, royal, monumental, hyperrealistic, exceptional, visually stunning"
Output
Performance Metrics
107.36s
Prediction Time
107.35s
Total Time
All Input Parameters
{ "seed": -1, "steps": 25, "width": 768, "frames": 16, "height": 512, "prompt": "a medium shot of a vibrant coral reef with a variety of marine life, rainbow, visual effects, prores, cineon, royal, monumental, hyperrealistic, exceptional, visually stunning", "base_model": "realisticVisionV20_v20", "guidance_scale": 7.5, "negative_prompt": "", "pan_up_motion_strength": 0, "zoom_in_motion_strength": 0, "pan_down_motion_strength": 0, "pan_left_motion_strength": 0, "zoom_out_motion_strength": 0, "pan_right_motion_strength": 0.75, "rolling_clockwise_motion_strength": 0, "rolling_anticlockwise_motion_strength": 0 }
Input Parameters
- seed
- Seed for different images and reproducibility. Use -1 to randomise seed
- steps
- Number of inference steps
- width
- Width in pixels
- frames
- Length of the video in frames (playback is at 8 fps e.g. 16 frames @ 8 fps is 2 seconds)
- height
- Height in pixels
- prompt
- base_model
- Select a base model (DreamBooth checkpoint)
- output_format
- Output format of the video. Can be 'mp4' or 'gif'
- guidance_scale
- Guidance Scale. How closely do we want to adhere to the prompt and its contents
- negative_prompt
- pan_up_motion_strength
- Strength of Pan Up Motion LoRA. 0 disables the LoRA
- zoom_in_motion_strength
- Strength of Zoom In Motion LoRA. 0 disables the LoRA
- pan_down_motion_strength
- Strength of Pan Down Motion LoRA. 0 disables the LoRA
- pan_left_motion_strength
- Strength of Pan Left Motion LoRA. 0 disables the LoRA
- zoom_out_motion_strength
- Strength of Zoom Out Motion LoRA. 0 disables the LoRA
- pan_right_motion_strength
- Strength of Pan Right Motion LoRA. 0 disables the LoRA
- rolling_clockwise_motion_strength
- Strength of Rolling Clockwise Motion LoRA. 0 disables the LoRA
- rolling_anticlockwise_motion_strength
- Strength of Rolling Anticlockwise Motion LoRA. 0 disables the LoRA
Output Schema
Output
Example Execution Logs
-------------------------------------------------------------------------------- Cog: inference_config: "configs/inference/inference-v2.yaml" motion_module: - "models/Motion_Module/mm_sd_v15_v2.ckpt" motion_module_lora_configs: - path: "models/MotionLoRA/v2_lora_PanRight.ckpt" alpha: 0.75 dreambooth_path: "models/DreamBooth_LoRA/realisticVisionV20_v20.safetensors" lora_model_path: "" seed: -1 steps: 25 guidance_scale: 7.5 prompt: - "a medium shot of a vibrant coral reef with a variety of marine life, rainbow, visual effects, prores, cineon, royal, monumental, hyperrealistic, exceptional, visually stunning" n_prompt: - "" -------------------------------------------------------------------------------- current seed: 14398808075592566791 sampling a medium shot of a vibrant coral reef with a variety of marine life, rainbow, visual effects, prores, cineon, royal, monumental, hyperrealistic, exceptional, visually stunning ... 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:04<01:38, 4.11s/it] 8%|▊ | 2/25 [00:08<01:34, 4.12s/it] 12%|█▏ | 3/25 [00:12<01:30, 4.12s/it] 16%|█▌ | 4/25 [00:16<01:26, 4.12s/it] 20%|██ | 5/25 [00:20<01:22, 4.12s/it] 24%|██▍ | 6/25 [00:24<01:18, 4.12s/it] 28%|██▊ | 7/25 [00:28<01:14, 4.12s/it] 32%|███▏ | 8/25 [00:32<01:10, 4.12s/it] 36%|███▌ | 9/25 [00:37<01:05, 4.12s/it] 40%|████ | 10/25 [00:41<01:01, 4.12s/it] 44%|████▍ | 11/25 [00:45<00:57, 4.13s/it] 48%|████▊ | 12/25 [00:49<00:53, 4.13s/it] 52%|█████▏ | 13/25 [00:53<00:49, 4.13s/it] 56%|█████▌ | 14/25 [00:57<00:45, 4.13s/it] 60%|██████ | 15/25 [01:01<00:41, 4.13s/it] 64%|██████▍ | 16/25 [01:06<00:37, 4.14s/it] 68%|██████▊ | 17/25 [01:10<00:33, 4.14s/it] 72%|███████▏ | 18/25 [01:14<00:28, 4.14s/it] 76%|███████▌ | 19/25 [01:18<00:24, 4.14s/it] 80%|████████ | 20/25 [01:22<00:20, 4.14s/it] 84%|████████▍ | 21/25 [01:26<00:16, 4.14s/it] 88%|████████▊ | 22/25 [01:30<00:12, 4.14s/it] 92%|█████████▏| 23/25 [01:35<00:08, 4.14s/it] 96%|█████████▌| 24/25 [01:39<00:04, 4.14s/it] 100%|██████████| 25/25 [01:43<00:00, 4.14s/it] 100%|██████████| 25/25 [01:43<00:00, 4.13s/it] 0%| | 0/16 [00:00<?, ?it/s] 31%|███▏ | 5/16 [00:00<00:00, 26.35it/s] 50%|█████ | 8/16 [00:00<00:00, 12.33it/s] 62%|██████▎ | 10/16 [00:00<00:00, 10.37it/s] 75%|███████▌ | 12/16 [00:01<00:00, 9.33it/s] 88%|████████▊ | 14/16 [00:01<00:00, 8.72it/s] 94%|█████████▍| 15/16 [00:01<00:00, 8.47it/s] 100%|██████████| 16/16 [00:01<00:00, 8.21it/s] 100%|██████████| 16/16 [00:01<00:00, 9.73it/s] save to samples/99a6f7b49d305094d1391b37d153ab22-2023-10-03T15-47-58/sample/amediumshotofa.mp4
Version Details
- Version ID
269a616c8b0c2bbc12fc15fd51bb202b11e94ff0f7786c026aa905305c4ed9fb
- Version Created
- October 5, 2023