fofr/wan-14b-my-subconscious 🔢🖼️❓📝 → 🖼️
About
Example Output
Prompt:
"MY_SUBCONSCIOUS monster is swimming, realistic photo, animated"
Output
Performance Metrics
193.01s
Prediction Time
260.90s
Total Time
All Input Parameters
{
"frames": 81,
"prompt": "MY_SUBCONSCIOUS monster is swimming, realistic photo, animated",
"aspect_ratio": "16:9",
"sample_shift": 5,
"sample_steps": 30,
"negative_prompt": "",
"lora_strength_clip": 0.8,
"sample_guide_scale": 4,
"lora_strength_model": 0.3
}
Input Parameters
- seed
- Set a seed for reproducibility. Random by default.
- image
- Image to use as a starting frame for image to video generation.
- frames
- The number of frames to generate (1 to 5 seconds)
- prompt (required)
- Text prompt for video generation
- fast_mode
- Speed up generation with different levels of acceleration. Faster modes may degrade quality somewhat. The speedup is dependent on the content, so different videos may see different speedups.
- resolution
- The resolution of the video. 720p is not supported for 1.3b.
- aspect_ratio
- The aspect ratio of the video. 16:9, 9:16, 1:1, etc.
- sample_shift
- Sample shift factor
- sample_steps
- Number of generation steps. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts
- negative_prompt
- Things you do not want to see in your video
- replicate_weights
- Replicate LoRA weights to use. Leave blank to use the default weights.
- lora_strength_clip
- Strength of the LORA applied to the CLIP model. 0.0 is no LORA.
- sample_guide_scale
- Higher guide scale makes prompt adherence better, but can reduce variation
- lora_strength_model
- Strength of the LORA applied to the model. 0.0 is no LORA.
Output Schema
Output
Example Execution Logs
Random seed set to: 2293881177
2025-03-12T19:42:51Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp654rau3v/weights url=https://replicate.delivery/xezq/qocyf3gptqQwJqBXaeMVS8kESLBmeIjvnqrFboh1CNigawvoA/trained_model.tar
2025-03-12T19:42:55Z | INFO | [ Complete ] dest=/tmp/tmp654rau3v/weights size="307 MB" total_elapsed=4.600s url=https://replicate.delivery/xezq/qocyf3gptqQwJqBXaeMVS8kESLBmeIjvnqrFboh1CNigawvoA/trained_model.tar
Checking inputs
====================================
Checking weights
✅ 2f613a6130046d67cede16f086db3550.safetensors exists in loras directory
✅ wan2.1_t2v_14B_bf16.safetensors exists in ComfyUI/models/diffusion_models
✅ wan_2.1_vae.safetensors exists in ComfyUI/models/vae
✅ umt5_xxl_fp16.safetensors exists in ComfyUI/models/text_encoders
====================================
Running workflow
[ComfyUI] got prompt
Executing node 39, title: Load VAE, class type: VAELoader
[ComfyUI] Using pytorch attention in VAE
[ComfyUI] Using pytorch attention in VAE
[ComfyUI] VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
Executing node 40, title: EmptyHunyuanLatentVideo, class type: EmptyHunyuanLatentVideo
Executing node 38, title: Load CLIP, class type: CLIPLoader
[ComfyUI] CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[ComfyUI] Requested to load WanTEModel
Executing node 7, title: CLIP Text Encode (Negative Prompt), class type: CLIPTextEncode
[ComfyUI] loaded completely 141327.4875 10835.4765625 True
Executing node 37, title: Load Diffusion Model, class type: UNETLoader
[ComfyUI] model weight dtype torch.float16, manual cast: None
[ComfyUI] model_type FLOW
Executing node 53, title: WanVideo Enhance A Video (native), class type: WanVideoEnhanceAVideoKJ
Executing node 54, title: WanVideo Tea Cache (native), class type: WanVideoTeaCacheKJ
Executing node 49, title: Load LoRA, class type: LoraLoader
[ComfyUI] Requested to load WanTEModel
Executing node 6, title: CLIP Text Encode (Positive Prompt), class type: CLIPTextEncode
[ComfyUI] loaded completely 141069.4875 10835.4765625 True
Executing node 48, title: ModelSamplingSD3, class type: ModelSamplingSD3
Executing node 3, title: KSampler, class type: KSampler
[ComfyUI] Requested to load WAN21
[ComfyUI] loaded completely 124343.96281542968 27251.406372070312 True
[ComfyUI]
[ComfyUI] 0%| | 0/30 [00:00<?, ?it/s]
[ComfyUI] 3%|▎ | 1/30 [00:07<03:51, 7.98s/it]
[ComfyUI] 7%|▋ | 2/30 [00:17<04:07, 8.85s/it]
[ComfyUI] 10%|█ | 3/30 [00:27<04:08, 9.20s/it]
[ComfyUI] TeaCache: Initialized
[ComfyUI]
[ComfyUI] 13%|█▎ | 4/30 [00:39<04:30, 10.41s/it]
[ComfyUI] 20%|██ | 6/30 [00:49<03:00, 7.53s/it]
[ComfyUI] 27%|██▋ | 8/30 [00:59<02:21, 6.43s/it]
[ComfyUI] 33%|███▎ | 10/30 [01:09<01:57, 5.88s/it]
[ComfyUI] 40%|████ | 12/30 [01:19<01:40, 5.57s/it]
[ComfyUI] 47%|████▋ | 14/30 [01:29<01:25, 5.37s/it]
[ComfyUI] 53%|█████▎ | 16/30 [01:39<01:13, 5.24s/it]
[ComfyUI] 60%|██████ | 18/30 [01:49<01:01, 5.16s/it]
[ComfyUI] 67%|██████▋ | 20/30 [01:59<00:51, 5.11s/it]
[ComfyUI] 73%|███████▎ | 22/30 [02:08<00:40, 5.07s/it]
[ComfyUI] 80%|████████ | 24/30 [02:18<00:30, 5.05s/it]
[ComfyUI] 87%|████████▋ | 26/30 [02:28<00:20, 5.03s/it]
[ComfyUI] 93%|█████████▎| 28/30 [02:38<00:10, 5.02s/it]
[ComfyUI] 100%|██████████| 30/30 [02:48<00:00, 5.01s/it]
[ComfyUI] 100%|██████████| 30/30 [02:48<00:00, 5.63s/it]
[ComfyUI] Requested to load WanVAE
Executing node 8, title: VAE Decode, class type: VAEDecode
[ComfyUI] loaded completely 98169.38668441772 242.02829551696777 True
Executing node 50, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] Prompt executed in 188.21 seconds
outputs: {'50': {'gifs': [{'filename': 'R8_Wan_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 16.0, 'workflow': 'R8_Wan_00001.png', 'fullpath': '/tmp/outputs/R8_Wan_00001.mp4'}]}}
====================================
R8_Wan_00001.png
R8_Wan_00001.mp4
Version Details
- Version ID
7b98fe85978ee4cfecb0a7e6552899ba3dfc54329364c6b00a8f1cc561d07bb3- Version Created
- March 12, 2025