lucataco/hunyuan-heygen-woman 🔢📝❓✓🖼️ → 🖼️
Performance
207.7sTypical run time
141Total runs
About
HunyuanVideo finetune of an AI avatar from Heygen
Example Output
Prompt:
"HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario."
Output
Performance Metrics
207.73s
Prediction Time
235.26s
Total Time
All Input Parameters
{
"crf": 19,
"steps": 30,
"width": 960,
"height": 544,
"prompt": "HGW woman with long, dark hair, tied back neatly, wearing a black jacket over a light top. She stands against a simple, gradient blue background, appearing calm and composed, possibly in a casual setting or an interview scenario.",
"lora_url": "",
"flow_shift": 9,
"frame_rate": 20,
"num_frames": 49,
"force_offload": true,
"lora_strength": 1,
"guidance_scale": 6,
"denoise_strength": 1
}
Input Parameters
- crf
- CRF (quality) for H264 encoding. Lower values = higher quality.
- seed
- Set a seed for reproducibility. Random by default.
- steps
- Number of diffusion steps.
- width
- Width for the generated video.
- height
- Height for the generated video.
- prompt
- The text prompt describing your video scene.
- lora_url
- A URL pointing to your LoRA .safetensors file or a Hugging Face repo (e.g. 'user/repo' - uses the first .safetensors file).
- scheduler
- Algorithm used to generate the video frames.
- flow_shift
- Video continuity factor (flow).
- frame_rate
- Video frame rate.
- num_frames
- How many frames (duration) in the resulting video.
- enhance_end
- When to end enhancement in the video. Must be greater than enhance_start.
- enhance_start
- When to start enhancement in the video. Must be less than enhance_end.
- force_offload
- Whether to force model layers offloaded to CPU.
- lora_strength
- Scale/strength for your LoRA.
- enhance_double
- Apply enhancement across frame pairs.
- enhance_single
- Apply enhancement to individual frames.
- enhance_weight
- Strength of the video enhancement effect.
- guidance_scale
- Overall influence of text vs. model.
- denoise_strength
- Controls how strongly noise is applied each step.
- replicate_weights
- A .tar file containing LoRA weights from replicate.
Output Schema
Output
Example Execution Logs
Random seed set to: 238810062
Checking inputs
====================================
Checking weights
✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae
✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models
====================================
Running workflow
[ComfyUI] got prompt
Executing node 7, title: HunyuanVideo VAE Loader, class type: HyVideoVAELoader
[ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14
Executing node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder
[ComfyUI] Text encoder to dtype: torch.float16
[ComfyUI] Loading tokenizer (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14
[ComfyUI] Loading text encoder model (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer
[ComfyUI]
[ComfyUI] Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]
[ComfyUI] Loading checkpoint shards: 25%|██▌ | 1/4 [00:00<00:01, 1.66it/s]
[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.72it/s]
[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.74it/s]
[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.54it/s]
[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.16it/s]
[ComfyUI] Text encoder to dtype: torch.float16
[ComfyUI] Loading tokenizer (llm) from: /src/ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer
Executing node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode
[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 48
[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 50
Executing node 41, title: HunyuanVideo Lora Select, class type: HyVideoLoraSelect
Executing node 1, title: HunyuanVideo Model Loader, class type: HyVideoModelLoader
[ComfyUI] model_type FLOW
[ComfyUI] Using accelerate to load and assign model weights to device...
[ComfyUI] Loading LoRA: lora_comfyui with strength: 1.0
[ComfyUI] Requested to load HyVideoModel
[ComfyUI] Loading 1 new model
[ComfyUI] loaded completely 0.0 12555.953247070312 True
[ComfyUI] Input (height, width, video_length) = (544, 960, 49)
Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler
[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 30 inference steps
[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])
[ComfyUI]
[ComfyUI] 0%| | 0/30 [00:00<?, ?it/s]
[ComfyUI] 3%|▎ | 1/30 [00:04<01:59, 4.12s/it]
[ComfyUI] 7%|▋ | 2/30 [00:09<02:18, 4.95s/it]
[ComfyUI] 10%|█ | 3/30 [00:15<02:20, 5.21s/it]
[ComfyUI] 13%|█▎ | 4/30 [00:20<02:18, 5.34s/it]
[ComfyUI] 17%|█▋ | 5/30 [00:26<02:15, 5.41s/it]
[ComfyUI] 20%|██ | 6/30 [00:31<02:10, 5.45s/it]
[ComfyUI] 23%|██▎ | 7/30 [00:37<02:05, 5.47s/it]
[ComfyUI] 27%|██▋ | 8/30 [00:42<02:00, 5.49s/it]
[ComfyUI] 30%|███ | 9/30 [00:48<01:55, 5.50s/it]
[ComfyUI] 33%|███▎ | 10/30 [00:53<01:50, 5.50s/it]
[ComfyUI] 37%|███▋ | 11/30 [00:59<01:44, 5.51s/it]
[ComfyUI] 40%|████ | 12/30 [01:04<01:39, 5.51s/it]
[ComfyUI] 43%|████▎ | 13/30 [01:10<01:33, 5.52s/it]
[ComfyUI] 47%|████▋ | 14/30 [01:15<01:28, 5.52s/it]
[ComfyUI] 50%|█████ | 15/30 [01:21<01:22, 5.52s/it]
[ComfyUI] 53%|█████▎ | 16/30 [01:26<01:17, 5.52s/it]
[ComfyUI] 57%|█████▋ | 17/30 [01:32<01:11, 5.52s/it]
[ComfyUI] 60%|██████ | 18/30 [01:38<01:06, 5.52s/it]
[ComfyUI] 63%|██████▎ | 19/30 [01:43<01:00, 5.52s/it]
[ComfyUI] 67%|██████▋ | 20/30 [01:49<00:55, 5.52s/it]
[ComfyUI] 70%|███████ | 21/30 [01:54<00:49, 5.52s/it]
[ComfyUI] 73%|███████▎ | 22/30 [02:00<00:44, 5.52s/it]
[ComfyUI] 77%|███████▋ | 23/30 [02:05<00:38, 5.52s/it]
[ComfyUI] 80%|████████ | 24/30 [02:11<00:33, 5.52s/it]
[ComfyUI] 83%|████████▎ | 25/30 [02:16<00:27, 5.52s/it]
[ComfyUI] 87%|████████▋ | 26/30 [02:22<00:22, 5.52s/it]
[ComfyUI] 90%|█████████ | 27/30 [02:27<00:16, 5.52s/it]
[ComfyUI] 93%|█████████▎| 28/30 [02:33<00:11, 5.52s/it]
[ComfyUI] 97%|█████████▋| 29/30 [02:38<00:05, 5.52s/it]
[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.52s/it]
[ComfyUI] 100%|██████████| 30/30 [02:44<00:00, 5.48s/it]
[ComfyUI] Allocated memory: memory=12.760 GB
[ComfyUI] Max allocated memory: max_memory=18.839 GB
[ComfyUI] Max reserved memory: max_reserved=20.719 GB
Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode
[ComfyUI]
[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]
[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:03, 1.52s/it]
[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:03<00:01, 1.63s/it]
[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.41s/it]
[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.46s/it]
[ComfyUI]
[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 33%|███▎ | 1/3 [00:00<00:00, 7.80it/s]
Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 18.11it/s]
[ComfyUI] Prompt executed in 201.68 seconds
outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 20.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}
====================================
HunyuanVideo_00001.png
HunyuanVideo_00001.mp4
Version Details
- Version ID
ac08c6bb6a71f2f02e0d4951709d634b1df0a9f3781ac5eefe2c2b293bdae37b- Version Created
- January 12, 2025