fofr/hunyuan-cyberpunk-mod 🔢📝❓✓🖼️ → 🖼️
About
Hunyuan fine-tuned on Cyberpunk 2077 photorealistic graphics mods, use CYB77 keyword
Example Output
Prompt:
"In the style of CYB77, first person view of a gunfight in a cyberpunk city"
Output
Performance Metrics
512.16s
Prediction Time
573.60s
Total Time
All Input Parameters
{
"crf": 19,
"steps": 50,
"width": 854,
"height": 480,
"prompt": "In the style of CYB77, first person view of a gunfight in a cyberpunk city",
"lora_url": "",
"flow_shift": 9,
"frame_rate": 24,
"num_frames": 85,
"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: 2729311902
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
Executing node 16, title: (Down)Load HunyuanVideo TextEncoder, class type: DownloadAndLoadHyVideoTextEncoder
[ComfyUI] Loading text encoder model (clipL) from: /src/ComfyUI/models/clip/clip-vit-large-patch14
[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, 1.69it/s]
[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.74it/s]
[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.77it/s]
[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.22it/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: 21
[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 22
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) = (480, 854, 85)
Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler
[ComfyUI] Sampling 85 frames in 22 latents at 864x480 with 50 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%| | 0/50 [00:00<?, ?it/s]
[ComfyUI] 2%|▏ | 1/50 [00:07<05:46, 7.06s/it]
[ComfyUI] 4%|▍ | 2/50 [00:16<06:45, 8.44s/it]
[ComfyUI] 6%|▌ | 3/50 [00:25<06:57, 8.88s/it]
[ComfyUI] 8%|▊ | 4/50 [00:35<06:58, 9.09s/it]
[ComfyUI] 10%|█ | 5/50 [00:44<06:54, 9.21s/it]
[ComfyUI] 12%|█▏ | 6/50 [00:54<06:48, 9.28s/it]
[ComfyUI] 14%|█▍ | 7/50 [01:03<06:40, 9.32s/it]
[ComfyUI] 16%|█▌ | 8/50 [01:12<06:32, 9.34s/it]
[ComfyUI] 18%|█▊ | 9/50 [01:22<06:23, 9.36s/it]
[ComfyUI] 20%|██ | 10/50 [01:31<06:14, 9.37s/it]
[ComfyUI] 22%|██▏ | 11/50 [01:41<06:05, 9.38s/it]
[ComfyUI] 24%|██▍ | 12/50 [01:50<05:56, 9.38s/it]
[ComfyUI] 26%|██▌ | 13/50 [01:59<05:47, 9.39s/it]
[ComfyUI] 28%|██▊ | 14/50 [02:09<05:38, 9.39s/it]
[ComfyUI] 30%|███ | 15/50 [02:18<05:28, 9.39s/it]
[ComfyUI] 32%|███▏ | 16/50 [02:28<05:19, 9.40s/it]
[ComfyUI] 34%|███▍ | 17/50 [02:37<05:10, 9.40s/it]
[ComfyUI] 36%|███▌ | 18/50 [02:46<05:00, 9.40s/it]
[ComfyUI] 38%|███▊ | 19/50 [02:56<04:51, 9.39s/it]
[ComfyUI] 40%|████ | 20/50 [03:05<04:41, 9.39s/it]
[ComfyUI] 42%|████▏ | 21/50 [03:15<04:32, 9.39s/it]
[ComfyUI] 44%|████▍ | 22/50 [03:24<04:23, 9.39s/it]
[ComfyUI] 46%|████▌ | 23/50 [03:33<04:13, 9.39s/it]
[ComfyUI] 48%|████▊ | 24/50 [03:43<04:04, 9.39s/it]
[ComfyUI] 50%|█████ | 25/50 [03:52<03:54, 9.39s/it]
[ComfyUI] 52%|█████▏ | 26/50 [04:02<03:45, 9.39s/it]
[ComfyUI] 54%|█████▍ | 27/50 [04:11<03:35, 9.39s/it]
[ComfyUI] 56%|█████▌ | 28/50 [04:20<03:26, 9.39s/it]
[ComfyUI] 58%|█████▊ | 29/50 [04:30<03:17, 9.39s/it]
[ComfyUI] 60%|██████ | 30/50 [04:39<03:07, 9.39s/it]
[ComfyUI] 62%|██████▏ | 31/50 [04:48<02:58, 9.39s/it]
[ComfyUI] 64%|██████▍ | 32/50 [04:58<02:49, 9.39s/it]
[ComfyUI] 66%|██████▌ | 33/50 [05:07<02:39, 9.39s/it]
[ComfyUI] 68%|██████▊ | 34/50 [05:17<02:30, 9.39s/it]
[ComfyUI] 70%|███████ | 35/50 [05:26<02:20, 9.39s/it]
[ComfyUI] 72%|███████▏ | 36/50 [05:35<02:11, 9.39s/it]
[ComfyUI] 74%|███████▍ | 37/50 [05:45<02:02, 9.39s/it]
[ComfyUI] 76%|███████▌ | 38/50 [05:54<01:52, 9.39s/it]
[ComfyUI] 78%|███████▊ | 39/50 [06:04<01:43, 9.39s/it]
[ComfyUI] 80%|████████ | 40/50 [06:13<01:33, 9.39s/it]
[ComfyUI] 82%|████████▏ | 41/50 [06:22<01:24, 9.39s/it]
[ComfyUI] 84%|████████▍ | 42/50 [06:32<01:15, 9.39s/it]
[ComfyUI] 86%|████████▌ | 43/50 [06:41<01:05, 9.39s/it]
[ComfyUI] 88%|████████▊ | 44/50 [06:51<00:56, 9.39s/it]
[ComfyUI] 90%|█████████ | 45/50 [07:00<00:46, 9.39s/it]
[ComfyUI] 92%|█████████▏| 46/50 [07:09<00:37, 9.39s/it]
[ComfyUI] 94%|█████████▍| 47/50 [07:19<00:28, 9.39s/it]
[ComfyUI] 96%|█████████▌| 48/50 [07:28<00:18, 9.39s/it]
[ComfyUI] 98%|█████████▊| 49/50 [07:37<00:09, 9.39s/it]
[ComfyUI] 100%|██████████| 50/50 [07:47<00:00, 9.39s/it]
[ComfyUI] 100%|██████████| 50/50 [07:47<00:00, 9.35s/it]
[ComfyUI] Allocated memory: memory=12.762 GB
[ComfyUI] Max allocated memory: max_memory=22.439 GB
[ComfyUI] Max reserved memory: max_reserved=26.000 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, 1.97s/it]
[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:04<00:02, 2.04s/it]
[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.50s/it]
[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00, 1.64s/it]
[ComfyUI]
[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 36.46it/s]
[ComfyUI]
[ComfyUI] Decoding rows: 0%| | 0/3 [00:00<?, ?it/s]
[ComfyUI] Decoding rows: 33%|███▎ | 1/3 [00:01<00:02, 1.12s/it]
[ComfyUI] Decoding rows: 67%|██████▋ | 2/3 [00:02<00:01, 1.15s/it]
[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.17it/s]
[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:02<00:00, 1.08it/s]
[ComfyUI]
[ComfyUI] Blending tiles: 0%| | 0/3 [00:00<?, ?it/s]
Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 50.34it/s]
[ComfyUI] Prompt executed in 507.93 seconds
outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 24.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}
====================================
HunyuanVideo_00001.png
HunyuanVideo_00001.mp4
Version Details
- Version ID
6095a5a5a4f81bccbf320e1a68051984c5a3c126495493a6c9656acd7e6d55c8- Version Created
- January 9, 2025