mushroomfleet/xjx-tokyoracer 🔢📝❓✓🖼️ → 🖼️
About
Clasic JDM highway racing
Example Output
Prompt:
"xjx style video of custom cars, racing on tokyo highways at night, JDM style found footage"
Output
Performance Metrics
123.26s
Prediction Time
123.27s
Total Time
All Input Parameters
{
"crf": 19,
"steps": 35,
"width": 640,
"height": 360,
"prompt": "xjx style video of custom cars, racing on tokyo highways at night, JDM style found footage",
"lora_url": "",
"scheduler": "DPMSolverMultistepScheduler",
"flow_shift": 9,
"frame_rate": 24,
"num_frames": 73,
"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
[ComfyUI] 37%|███▋ | 13/35 [00:35<01:01, 2.77s/it]
[ComfyUI] 40%|████ | 14/35 [00:38<00:58, 2.78s/it]
Random seed set to: 2730847005
⚠️ Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements
�� USING REPLICATE WEIGHTS (preferred method)
🎯 USING REPLICATE WEIGHTS TAR FILE 🎯
----------------------------------------
📦 Processing replicate weights tar file...
🔄 Will rename LoRA to: replicate_d33f3398-f8a1-441b-8f16-0a9c57ba69c6.safetensors
📂 Extracting tar contents...
✅ Found lora_comfyui.safetensors in tar
✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_d33f3398-f8a1-441b-8f16-0a9c57ba69c6.safetensors
----------------------------------------
Checking inputs
====================================
Checking weights
✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models
✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae
====================================
Running workflow
[ComfyUI] 43%|████▎ | 15/35 [00:41<00:55, 2.78s/it]got prompt
[ComfyUI]
[ComfyUI] 46%|████▌ | 16/35 [00:43<00:52, 2.78s/it]
[ComfyUI] 46%|████▌ | 16/35 [00:43<00:52, 2.74s/it]
[ComfyUI] Processing interrupted
[ComfyUI] Prompt executed in 52.81 seconds
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_d33f3398-f8a1-441b-8f16-0a9c57ba69c6 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, 73)
[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.
Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler
[ComfyUI] Sampling 73 frames in 19 latents at 640x368 with 35 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%| | 0/35 [00:00<?, ?it/s]
[ComfyUI] 3%|▎ | 1/35 [00:02<01:34, 2.78s/it]
[ComfyUI] 6%|▌ | 2/35 [00:04<01:20, 2.44s/it]
[ComfyUI] 9%|▊ | 3/35 [00:07<01:22, 2.59s/it]
[ComfyUI] 11%|█▏ | 4/35 [00:10<01:22, 2.67s/it]
[ComfyUI] 14%|█▍ | 5/35 [00:13<01:21, 2.71s/it]
[ComfyUI] 17%|█▋ | 6/35 [00:16<01:19, 2.73s/it]
[ComfyUI] 20%|██ | 7/35 [00:18<01:16, 2.75s/it]
[ComfyUI] 23%|██▎ | 8/35 [00:21<01:14, 2.76s/it]
[ComfyUI] 26%|██▌ | 9/35 [00:24<01:11, 2.77s/it]
[ComfyUI] 29%|██▊ | 10/35 [00:27<01:09, 2.77s/it]
[ComfyUI] 31%|███▏ | 11/35 [00:29<01:06, 2.77s/it]
[ComfyUI] 34%|███▍ | 12/35 [00:32<01:03, 2.78s/it]
[ComfyUI] 37%|███▋ | 13/35 [00:35<01:01, 2.78s/it]
[ComfyUI] 40%|████ | 14/35 [00:38<00:58, 2.78s/it]
[ComfyUI] 43%|████▎ | 15/35 [00:41<00:55, 2.78s/it]
[ComfyUI] 46%|████▌ | 16/35 [00:43<00:52, 2.78s/it]
[ComfyUI] 49%|████▊ | 17/35 [00:46<00:50, 2.78s/it]
[ComfyUI] 51%|█████▏ | 18/35 [00:49<00:47, 2.78s/it]
[ComfyUI] 54%|█████▍ | 19/35 [00:52<00:44, 2.78s/it]
[ComfyUI] 57%|█████▋ | 20/35 [00:55<00:41, 2.78s/it]
[ComfyUI] 60%|██████ | 21/35 [00:57<00:38, 2.78s/it]
[ComfyUI] 63%|██████▎ | 22/35 [01:00<00:36, 2.78s/it]
[ComfyUI] 66%|██████▌ | 23/35 [01:03<00:33, 2.78s/it]
[ComfyUI] 69%|██████▊ | 24/35 [01:06<00:30, 2.78s/it]
[ComfyUI] 71%|███████▏ | 25/35 [01:08<00:27, 2.78s/it]
[ComfyUI] 74%|███████▍ | 26/35 [01:11<00:25, 2.78s/it]
[ComfyUI] 77%|███████▋ | 27/35 [01:14<00:22, 2.78s/it]
[ComfyUI] 80%|████████ | 28/35 [01:17<00:19, 2.78s/it]
[ComfyUI] 83%|████████▎ | 29/35 [01:20<00:16, 2.78s/it]
[ComfyUI] 86%|████████▌ | 30/35 [01:22<00:13, 2.78s/it]
[ComfyUI] 89%|████████▊ | 31/35 [01:25<00:11, 2.78s/it]
[ComfyUI] 91%|█████████▏| 32/35 [01:28<00:08, 2.78s/it]
[ComfyUI] 94%|█████████▍| 33/35 [01:31<00:05, 2.78s/it]
[ComfyUI] 97%|█████████▋| 34/35 [01:33<00:02, 2.78s/it]
[ComfyUI] 100%|██████████| 35/35 [01:36<00:00, 2.78s/it]
[ComfyUI] 100%|██████████| 35/35 [01:36<00:00, 2.76s/it]
[ComfyUI] Allocated memory: memory=12.301 GB
[ComfyUI] Max allocated memory: max_memory=15.577 GB
[ComfyUI] Max reserved memory: max_reserved=16.469 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, 25.95it/s]
[ComfyUI]
[ComfyUI] Decoding rows: 0%| | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows: 50%|█████ | 1/2 [00:00<00:00, 1.77it/s]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.09it/s]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00, 2.03it/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, 54.08it/s]
[ComfyUI] Prompt executed in 114.97 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
8ddc25bcae7976fba45e6418cbdcb699f9a4ec2f67c6bf9f3c3b5b3e1bf112c1- Version Created
- February 2, 2025