deepfates/hunyuan-game-of-thrones 🔢📝❓✓🖼️ → 🖼️
About
Hunyuan-Video model finetuned on Game of Thrones (2011). Trigger word is "GMFTH". Use "A video in the style of GMFTH, GMFTH" at the beginning of your prompt for best results
Example Output
Prompt:
"A video in the style of GMFTH, GMFTH The video clip features a woman standing outdoors in what appears to be a historical or rural setting. The lighting is warm and golden, suggesting that it is either early morning or late afternoon. The woman has long, wavy hair that is partially tied back, and she is wearing a blue top with a lace or embroidered neckline. The background is slightly blurred, but it shows wooden structures and a dirt path, indicating a rustic environment. The overall atmosphere is serene and contemplative."
Output
Performance Metrics
139.34s
Prediction Time
758.12s
Total Time
All Input Parameters
{
"seed": 12345,
"steps": 50,
"width": 640,
"height": 360,
"prompt": "A video in the style of GMFTH, GMFTH The video clip features a woman standing outdoors in what appears to be a historical or rural setting. The lighting is warm and golden, suggesting that it is either early morning or late afternoon. The woman has long, wavy hair that is partially tied back, and she is wearing a blue top with a lace or embroidered neckline. The background is slightly blurred, but it shows wooden structures and a dirt path, indicating a rustic environment. The overall atmosphere is serene and contemplative.",
"frame_rate": 16,
"num_frames": 66,
"lora_strength": 1,
"guidance_scale": 6
}
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
Seed set to: 12345
⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements
⚠️ Adjusted frame count from 66 to 65 to satisfy model requirements
�� USING REPLICATE WEIGHTS (preferred method)
🎯 USING REPLICATE WEIGHTS TAR FILE 🎯
----------------------------------------
📦 Processing replicate weights tar file...
🔄 Will rename LoRA to: replicate_a99a073e-778a-499f-8fff-55821eeb836d.safetensors
📂 Extracting tar contents...
✅ Found lora_comfyui.safetensors in tar
✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_a99a073e-778a-499f-8fff-55821eeb836d.safetensors
----------------------------------------
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 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode
[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 109
[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 77
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] The config attributes {'use_flow_sigmas': True, 'prediction_type': 'flow_prediction'} were passed to FlowMatchDiscreteScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
[ComfyUI] Using accelerate to load and assign model weights to device...
[ComfyUI] Loading LoRA: replicate_a99a073e-778a-499f-8fff-55821eeb836d with strength: 1.0
[ComfyUI] Requested to load HyVideoModel
[ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True
[ComfyUI] Input (height, width, video_length) = (368, 640, 65)
Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler
[ComfyUI] The config attributes {'reverse': True, 'solver': 'euler'} were passed to DPMSolverMultistepScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
[ComfyUI] Sampling 65 frames in 17 latents at 640x368 with 50 inference steps
[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('flow_shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['num_train_timesteps', 'n_tokens'])])[ComfyUI]
[ComfyUI] 0%| | 0/50 [00:00<?, ?it/s]
[ComfyUI] 2%|▏ | 1/50 [00:02<01:53, 2.31s/it]
[ComfyUI] 4%|▍ | 2/50 [00:04<01:37, 2.02s/it]
[ComfyUI] 6%|▌ | 3/50 [00:06<01:41, 2.15s/it]
[ComfyUI] 8%|▊ | 4/50 [00:08<01:41, 2.21s/it]
[ComfyUI] 10%|█ | 5/50 [00:11<01:40, 2.24s/it]
[ComfyUI] 12%|█▏ | 6/50 [00:13<01:39, 2.26s/it]
[ComfyUI] 14%|█▍ | 7/50 [00:15<01:37, 2.27s/it]
[ComfyUI] 16%|█▌ | 8/50 [00:17<01:35, 2.28s/it]
[ComfyUI] 18%|█▊ | 9/50 [00:20<01:33, 2.29s/it]
[ComfyUI] 20%|██ | 10/50 [00:22<01:31, 2.29s/it]
[ComfyUI] 22%|██▏ | 11/50 [00:24<01:29, 2.29s/it]
[ComfyUI] 24%|██▍ | 12/50 [00:27<01:27, 2.29s/it]
[ComfyUI] 26%|██▌ | 13/50 [00:29<01:24, 2.29s/it]
[ComfyUI] 28%|██▊ | 14/50 [00:31<01:22, 2.30s/it]
[ComfyUI] 30%|███ | 15/50 [00:34<01:20, 2.30s/it]
[ComfyUI] 32%|███▏ | 16/50 [00:36<01:18, 2.30s/it]
[ComfyUI] 34%|███▍ | 17/50 [00:38<01:15, 2.30s/it]
[ComfyUI] 36%|███▌ | 18/50 [00:40<01:13, 2.30s/it]
[ComfyUI] 38%|███▊ | 19/50 [00:43<01:11, 2.30s/it]
[ComfyUI] 40%|████ | 20/50 [00:45<01:08, 2.30s/it]
[ComfyUI] 42%|████▏ | 21/50 [00:47<01:06, 2.30s/it]
[ComfyUI] 44%|████▍ | 22/50 [00:50<01:04, 2.30s/it]
[ComfyUI] 46%|████▌ | 23/50 [00:52<01:02, 2.30s/it]
[ComfyUI] 48%|████▊ | 24/50 [00:54<00:59, 2.30s/it]
[ComfyUI] 50%|█████ | 25/50 [00:56<00:57, 2.30s/it]
[ComfyUI] 52%|█████▏ | 26/50 [00:59<00:55, 2.30s/it]
[ComfyUI] 54%|█████▍ | 27/50 [01:01<00:52, 2.30s/it]
[ComfyUI] 56%|█████▌ | 28/50 [01:03<00:50, 2.30s/it]
[ComfyUI] 58%|█████▊ | 29/50 [01:06<00:48, 2.30s/it]
[ComfyUI] 60%|██████ | 30/50 [01:08<00:45, 2.30s/it]
[ComfyUI] 62%|██████▏ | 31/50 [01:10<00:43, 2.30s/it]
[ComfyUI] 64%|██████▍ | 32/50 [01:13<00:41, 2.30s/it]
[ComfyUI] 66%|██████▌ | 33/50 [01:15<00:39, 2.30s/it]
[ComfyUI] 68%|██████▊ | 34/50 [01:17<00:36, 2.30s/it]
[ComfyUI] 70%|███████ | 35/50 [01:19<00:34, 2.30s/it]
[ComfyUI] 72%|███████▏ | 36/50 [01:22<00:32, 2.30s/it]
[ComfyUI] 74%|███████▍ | 37/50 [01:24<00:29, 2.30s/it]
[ComfyUI] 76%|███████▌ | 38/50 [01:26<00:27, 2.30s/it]
[ComfyUI] 78%|███████▊ | 39/50 [01:29<00:25, 2.30s/it]
[ComfyUI] 80%|████████ | 40/50 [01:31<00:22, 2.30s/it]
[ComfyUI] 82%|████████▏ | 41/50 [01:33<00:20, 2.30s/it]
[ComfyUI] 84%|████████▍ | 42/50 [01:36<00:18, 2.30s/it]
[ComfyUI] 86%|████████▌ | 43/50 [01:38<00:16, 2.30s/it]
[ComfyUI] 88%|████████▊ | 44/50 [01:40<00:13, 2.30s/it]
[ComfyUI] 90%|█████████ | 45/50 [01:42<00:11, 2.30s/it]
[ComfyUI] 92%|█████████▏| 46/50 [01:45<00:09, 2.30s/it]
[ComfyUI] 94%|█████████▍| 47/50 [01:47<00:06, 2.30s/it]
[ComfyUI] 96%|█████████▌| 48/50 [01:49<00:04, 2.30s/it]
[ComfyUI] 98%|█████████▊| 49/50 [01:52<00:02, 2.30s/it]
[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.30s/it]
[ComfyUI] 100%|██████████| 50/50 [01:54<00:00, 2.29s/it]
[ComfyUI] Allocated memory: memory=12.300 GB
[ComfyUI] Max allocated memory: max_memory=15.099 GB
[ComfyUI] Max reserved memory: max_reserved=16.344 GB
Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode
[ComfyUI]
[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:01<00:01, 1.46s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.24s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00, 1.27s/it]
[ComfyUI]
[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 25.91it/s]
[ComfyUI]
[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 2.55it/s]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 3.03it/s]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.95it/s]
[ComfyUI]
[ComfyUI] Blending tiles: 0%| | 0/2 [00:00<?, ?it/s]
Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 64.89it/s]
[ComfyUI] Prompt executed in 136.95 seconds
outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 16.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}
====================================
HunyuanVideo_00001.png
HunyuanVideo_00001.mp4
Version Details
- Version ID
cf2945dc3ea45f61f8187629035a59019c8a71d7252eee7d820655770d92ac51- Version Created
- January 24, 2025