mushroomfleet/fxf_tokyo_meet 🔢📝❓✓🖼️ → 🖼️
About
JDM style Car Meetup
Example Output
Prompt:
"video of a drift meet, FXF The video clip depicts a nighttime scene on a city highway. The camera follows a white sports car as it drives on the right side of the road, passing a black car with its headlights on. The white car has distinctive red taillights and a sleek, aerodynamic design. The highway is illuminated by streetlights and the headlights of the vehicles, creating a bright and dynamic atmosphere. In the background, tall buildings with numerous lights can be seen, indicating an urban setting. The overall scene in the style of FXF"
Output
Performance Metrics
1455.85s
Prediction Time
1482.64s
Total Time
All Input Parameters
{
"crf": 19,
"steps": 40,
"width": 1280,
"height": 720,
"prompt": "video of a drift meet, FXF The video clip depicts a nighttime scene on a city highway. The camera follows a white sports car as it drives on the right side of the road, passing a black car with its headlights on. The white car has distinctive red taillights and a sleek, aerodynamic design. The highway is illuminated by streetlights and the headlights of the vehicles, creating a bright and dynamic atmosphere. In the background, tall buildings with numerous lights can be seen, indicating an urban setting. The overall scene in the style of FXF",
"lora_url": "",
"scheduler": "DPMSolverMultistepScheduler",
"flow_shift": 9,
"frame_rate": 25,
"num_frames": 75,
"enhance_end": 1,
"enhance_start": 0,
"force_offload": true,
"lora_strength": 1,
"enhance_double": true,
"enhance_single": true,
"enhance_weight": 0.3,
"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: 1292014955
⚠️ Adjusted frame count from 75 to 77 to satisfy model requirements
�� USING REPLICATE WEIGHTS (preferred method)
🎯 USING REPLICATE WEIGHTS TAR FILE 🎯
----------------------------------------
📦 Processing replicate weights tar file...
🔄 Will rename LoRA to: replicate_72000e1f-bca1-4bbc-b767-343713bd8485.safetensors
📂 Extracting tar contents...
✅ Found lora_comfyui.safetensors in tar
✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_72000e1f-bca1-4bbc-b767-343713bd8485.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 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 42, title: HunyuanVideo Enhance A Video, class type: HyVideoEnhanceAVideo
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, 1.63it/s]
[ComfyUI] Loading checkpoint shards: 50%|█████ | 2/4 [00:01<00:01, 1.62it/s]
[ComfyUI] Loading checkpoint shards: 75%|███████▌ | 3/4 [00:01<00:00, 1.65it/s]
[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.45it/s]
[ComfyUI] Loading checkpoint shards: 100%|██████████| 4/4 [00:01<00:00, 2.07it/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: 113
[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_72000e1f-bca1-4bbc-b767-343713bd8485 with strength: 1.0
[ComfyUI] Requested to load HyVideoModel
[ComfyUI] loaded completely 9.5367431640625e+25 12555.953247070312 True
[ComfyUI] Input (height, width, video_length) = (720, 1280, 77)
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 77 frames in 20 latents at 1280x720 with 40 inference steps
[ComfyUI] Scheduler config: FrozenDict([('num_train_timesteps', 1000), ('flow_shift', 9.0), ('reverse', True), ('solver', 'euler'), ('n_tokens', None), ('_use_default_values', ['n_tokens', 'num_train_timesteps'])])
[ComfyUI]
[ComfyUI] 0%| | 0/40 [00:00<?, ?it/s]
[ComfyUI] 2%|▎ | 1/40 [00:35<22:49, 35.13s/it]
[ComfyUI] 5%|▌ | 2/40 [01:04<20:02, 31.64s/it]
[ComfyUI] 8%|▊ | 3/40 [01:39<20:26, 33.16s/it]
[ComfyUI] 10%|█ | 4/40 [02:14<20:19, 33.87s/it]
[ComfyUI] 12%|█▎ | 5/40 [02:49<19:59, 34.26s/it]
[ComfyUI] 15%|█▌ | 6/40 [03:24<19:32, 34.50s/it]
[ComfyUI] 18%|█▊ | 7/40 [03:59<19:03, 34.64s/it]
[ComfyUI] 20%|██ | 8/40 [04:34<18:31, 34.74s/it]
[ComfyUI] 22%|██▎ | 9/40 [05:09<17:59, 34.81s/it]
[ComfyUI] 25%|██▌ | 10/40 [05:43<17:25, 34.85s/it]
[ComfyUI] 28%|██▊ | 11/40 [06:18<16:51, 34.88s/it]
[ComfyUI] 30%|███ | 12/40 [06:53<16:17, 34.90s/it]
[ComfyUI] 32%|███▎ | 13/40 [07:28<15:42, 34.91s/it]
[ComfyUI] 35%|███▌ | 14/40 [08:03<15:08, 34.93s/it]
[ComfyUI] 38%|███▊ | 15/40 [08:38<14:33, 34.93s/it]
[ComfyUI] 40%|████ | 16/40 [09:13<13:58, 34.94s/it]
[ComfyUI] 42%|████▎ | 17/40 [09:48<13:23, 34.94s/it]
[ComfyUI] 45%|████▌ | 18/40 [10:23<12:48, 34.95s/it]
[ComfyUI] 48%|████▊ | 19/40 [10:58<12:13, 34.95s/it]
[ComfyUI] 50%|█████ | 20/40 [11:33<11:38, 34.95s/it]
[ComfyUI] 52%|█████▎ | 21/40 [12:08<11:03, 34.95s/it]
[ComfyUI] 55%|█████▌ | 22/40 [12:43<10:29, 34.95s/it]
[ComfyUI] 57%|█████▊ | 23/40 [13:18<09:54, 34.94s/it]
[ComfyUI] 60%|██████ | 24/40 [13:53<09:19, 34.95s/it]
[ComfyUI] 62%|██████▎ | 25/40 [14:28<08:44, 34.95s/it]
[ComfyUI] 65%|██████▌ | 26/40 [15:03<08:09, 34.95s/it]
[ComfyUI] 68%|██████▊ | 27/40 [15:38<07:34, 34.95s/it]
[ComfyUI] 70%|███████ | 28/40 [16:13<06:59, 34.95s/it]
[ComfyUI] 72%|███████▎ | 29/40 [16:47<06:24, 34.95s/it]
[ComfyUI] 75%|███████▌ | 30/40 [17:22<05:49, 34.95s/it]
[ComfyUI] 78%|███████▊ | 31/40 [17:57<05:14, 34.94s/it]
[ComfyUI] 80%|████████ | 32/40 [18:32<04:39, 34.95s/it]
[ComfyUI] 82%|████████▎ | 33/40 [19:07<04:04, 34.95s/it]
[ComfyUI] 85%|████████▌ | 34/40 [19:42<03:29, 34.95s/it]
[ComfyUI] 88%|████████▊ | 35/40 [20:17<02:54, 34.95s/it]
[ComfyUI] 90%|█████████ | 36/40 [20:52<02:19, 34.95s/it]
[ComfyUI] 92%|█████████▎| 37/40 [21:27<01:44, 34.94s/it]
[ComfyUI] 95%|█████████▌| 38/40 [22:02<01:09, 34.94s/it]
[ComfyUI] 98%|█████████▊| 39/40 [22:37<00:34, 34.94s/it]
[ComfyUI] 100%|██████████| 40/40 [23:12<00:00, 34.94s/it]
[ComfyUI] 100%|██████████| 40/40 [23:12<00:00, 34.81s/it]
[ComfyUI] Allocated memory: memory=12.780 GB
[ComfyUI] Max allocated memory: max_memory=44.503 GB
[ComfyUI] Max reserved memory: max_reserved=58.906 GB
Executing node 5, title: HunyuanVideo Decode, class type: HyVideoDecode
[ComfyUI]
[ComfyUI] Decoding rows: 0%| | 0/4 [00:00<?, ?it/s]
[ComfyUI] Decoding rows: 25%|██▌ | 1/4 [00:02<00:08, 2.94s/it]
[ComfyUI] Decoding rows: 50%|█████ | 2/4 [00:06<00:06, 3.02s/it]
[ComfyUI] Decoding rows: 75%|███████▌ | 3/4 [00:09<00:03, 3.05s/it]
[ComfyUI] Decoding rows: 100%|██████████| 4/4 [00:10<00:00, 2.56s/it]
[ComfyUI] Decoding rows: 100%|██████████| 4/4 [00:10<00:00, 2.73s/it]
[ComfyUI]
[ComfyUI] Blending tiles: 0%| | 0/4 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 25%|██▌ | 1/4 [00:00<00:00, 9.71it/s]
[ComfyUI] Blending tiles: 100%|██████████| 4/4 [00:00<00:00, 21.59it/s]
[ComfyUI]
[ComfyUI] Decoding rows: 0%| | 0/4 [00:00<?, ?it/s]
[ComfyUI] Decoding rows: 25%|██▌ | 1/4 [00:01<00:03, 1.31s/it]
[ComfyUI] Decoding rows: 50%|█████ | 2/4 [00:02<00:02, 1.35s/it]
[ComfyUI] Decoding rows: 75%|███████▌ | 3/4 [00:04<00:01, 1.37s/it]
[ComfyUI] Decoding rows: 100%|██████████| 4/4 [00:04<00:00, 1.15s/it]
[ComfyUI] Decoding rows: 100%|██████████| 4/4 [00:04<00:00, 1.22s/it]
[ComfyUI]
[ComfyUI] Blending tiles: 0%| | 0/4 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 100%|██████████| 4/4 [00:00<00:00, 31.98it/s]
Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] Blending tiles: 100%|██████████| 4/4 [00:00<00:00, 31.93it/s]
[ComfyUI] Prompt executed in 1445.91 seconds
outputs: {'34': {'gifs': [{'filename': 'HunyuanVideo_00001.mp4', 'subfolder': '', 'type': 'output', 'format': 'video/h264-mp4', 'frame_rate': 25.0, 'workflow': 'HunyuanVideo_00001.png', 'fullpath': '/tmp/outputs/HunyuanVideo_00001.mp4'}]}}
====================================
HunyuanVideo_00001.png
HunyuanVideo_00001.mp4
Version Details
- Version ID
49eaa9fb2e5b4a1b4963b76e578210673030fdf6158c1b7cb7cb1791eeedd550- Version Created
- February 4, 2025