derickson/dn2trl_1 🔢📝❓✓🖼️ → 🖼️

▶️ 4 runs 📅 Feb 2025 ⚙️ Cog 0.13.6
text-to-video video-lora-training

About

Dune 2 Trailer LoRA for hunyuan-video-lora. Trigger word is DN2TRL

Example Output

Prompt:

"in the style of DN2TRL, a warrior stands on a sand hill looking at a crowd of enemies. transition to a cave scene with a bald villain holding a knife. transition to an explosion in a canyon"

Output

Performance Metrics

1209.45s Prediction Time
1209.46s Total Time
All Input Parameters 
{
  "crf": 19,
  "steps": 50,
  "width": 640,
  "height": 360,
  "prompt": "in the style of DN2TRL, a warrior stands on a sand hill looking at a crowd of enemies. transition to a cave scene with a bald villain holding a knife. transition to an explosion in a canyon",
  "lora_url": "",
  "scheduler": "DPMSolverMultistepScheduler",
  "flow_shift": 9,
  "frame_rate": 16,
  "num_frames": 250,
  "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 Type: integerDefault: 19Range: 0 - 51
CRF (quality) for H264 encoding. Lower values = higher quality.
seed Type: integer
Set a seed for reproducibility. Random by default.
steps Type: integerDefault: 50Range: 1 - 150
Number of diffusion steps.
width Type: integerDefault: 640Range: 64 - 1536
Width for the generated video.
height Type: integerDefault: 360Range: 64 - 1024
Height for the generated video.
prompt Type: stringDefault:
The text prompt describing your video scene.
lora_url Type: stringDefault:
A URL pointing to your LoRA .safetensors file or a Hugging Face repo (e.g. 'user/repo' - uses the first .safetensors file).
scheduler Default: DPMSolverMultistepScheduler
Algorithm used to generate the video frames.
flow_shift Type: integerDefault: 9Range: 0 - 20
Video continuity factor (flow).
frame_rate Type: integerDefault: 16Range: 1 - 60
Video frame rate.
num_frames Type: integerDefault: 33Range: 1 - 1440
How many frames (duration) in the resulting video.
enhance_end Type: numberDefault: 1Range: 0 - 1
When to end enhancement in the video. Must be greater than enhance_start.
enhance_start Type: numberDefault: 0Range: 0 - 1
When to start enhancement in the video. Must be less than enhance_end.
force_offload Type: booleanDefault: true
Whether to force model layers offloaded to CPU.
lora_strength Type: numberDefault: 1Range: -10 - 10
Scale/strength for your LoRA.
enhance_double Type: booleanDefault: true
Apply enhancement across frame pairs.
enhance_single Type: booleanDefault: true
Apply enhancement to individual frames.
enhance_weight Type: numberDefault: 0.3Range: 0 - 2
Strength of the video enhancement effect.
guidance_scale Type: numberDefault: 6Range: 0 - 30
Overall influence of text vs. model.
denoise_strength Type: numberDefault: 1Range: 0 - 2
Controls how strongly noise is applied each step.
replicate_weights Type: string
A .tar file containing LoRA weights from replicate.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Random seed set to: 2139277422
⚠️  Adjusted dimensions from 640x360 to 640x368 to satisfy model requirements
⚠️  Adjusted frame count from 250 to 249 to satisfy model requirements
�� USING REPLICATE WEIGHTS (preferred method)
🎯 USING REPLICATE WEIGHTS TAR FILE 🎯
----------------------------------------
📦 Processing replicate weights tar file...
🔄 Will rename LoRA to: replicate_8f63e60b-6819-40cb-9fae-8300efd77eb7.safetensors
📂 Extracting tar contents...
✅ Found lora_comfyui.safetensors in tar
✨ Successfully copied LoRA to: ComfyUI/models/loras/replicate_8f63e60b-6819-40cb-9fae-8300efd77eb7.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] got prompt
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_8f63e60b-6819-40cb-9fae-8300efd77eb7 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, 249)
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 249 frames in 63 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', ['n_tokens', 'num_train_timesteps'])])
[ComfyUI]
[ComfyUI] 0%|          | 0/50 [00:00<?, ?it/s]
[ComfyUI] 2%|▏         | 1/50 [00:23<19:05, 23.38s/it]
[ComfyUI] 4%|▍         | 2/50 [00:42<16:41, 20.86s/it]
[ComfyUI] 6%|▌         | 3/50 [01:05<17:13, 21.99s/it]
[ComfyUI] 8%|▊         | 4/50 [01:29<17:16, 22.53s/it]
[ComfyUI] 10%|█         | 5/50 [01:52<17:06, 22.82s/it]
[ComfyUI] 12%|█▏        | 6/50 [02:15<16:51, 22.98s/it]
[ComfyUI] 14%|█▍        | 7/50 [02:39<16:32, 23.08s/it]
[ComfyUI] 16%|█▌        | 8/50 [03:02<16:12, 23.16s/it]
[ComfyUI] 18%|█▊        | 9/50 [03:25<15:51, 23.22s/it]
[ComfyUI] 20%|██        | 10/50 [03:49<15:30, 23.26s/it]
[ComfyUI] 22%|██▏       | 11/50 [04:12<15:08, 23.29s/it]
[ComfyUI] 24%|██▍       | 12/50 [04:35<14:45, 23.30s/it]
[ComfyUI] 26%|██▌       | 13/50 [04:59<14:22, 23.32s/it]
[ComfyUI] 28%|██▊       | 14/50 [05:22<13:59, 23.33s/it]
[ComfyUI] 30%|███       | 15/50 [05:45<13:36, 23.33s/it]
[ComfyUI] 32%|███▏      | 16/50 [06:09<13:13, 23.33s/it]
[ComfyUI] 34%|███▍      | 17/50 [06:32<12:50, 23.33s/it]
[ComfyUI] 36%|███▌      | 18/50 [06:55<12:26, 23.34s/it]
[ComfyUI] 38%|███▊      | 19/50 [07:19<12:03, 23.34s/it]
[ComfyUI] 40%|████      | 20/50 [07:42<11:40, 23.34s/it]
[ComfyUI] 42%|████▏     | 21/50 [08:05<11:16, 23.34s/it]
[ComfyUI] 44%|████▍     | 22/50 [08:29<10:53, 23.34s/it]
[ComfyUI] 46%|████▌     | 23/50 [08:52<10:30, 23.34s/it]
[ComfyUI] 48%|████▊     | 24/50 [09:15<10:06, 23.35s/it]
[ComfyUI] 50%|█████     | 25/50 [09:39<09:43, 23.35s/it]
[ComfyUI] 52%|█████▏    | 26/50 [10:02<09:20, 23.34s/it]
[ComfyUI] 54%|█████▍    | 27/50 [10:25<08:56, 23.34s/it]
[ComfyUI] 56%|█████▌    | 28/50 [10:49<08:33, 23.34s/it]
[ComfyUI] 58%|█████▊    | 29/50 [11:12<08:10, 23.34s/it]
[ComfyUI] 60%|██████    | 30/50 [11:35<07:46, 23.34s/it]
[ComfyUI] 62%|██████▏   | 31/50 [11:59<07:23, 23.34s/it]
[ComfyUI] 64%|██████▍   | 32/50 [12:22<07:00, 23.34s/it]
[ComfyUI] 66%|██████▌   | 33/50 [12:46<06:36, 23.34s/it]
[ComfyUI] 68%|██████▊   | 34/50 [13:09<06:13, 23.34s/it]
[ComfyUI] 70%|███████   | 35/50 [13:32<05:50, 23.34s/it]
[ComfyUI] 72%|███████▏  | 36/50 [13:56<05:26, 23.34s/it]
[ComfyUI] 74%|███████▍  | 37/50 [14:19<05:03, 23.34s/it]
[ComfyUI] 76%|███████▌  | 38/50 [14:42<04:40, 23.34s/it]
[ComfyUI] 78%|███████▊  | 39/50 [15:06<04:16, 23.34s/it]
[ComfyUI] 80%|████████  | 40/50 [15:29<03:53, 23.35s/it]
[ComfyUI] 82%|████████▏ | 41/50 [15:52<03:30, 23.35s/it]
[ComfyUI] 84%|████████▍ | 42/50 [16:16<03:07, 23.46s/it]
[ComfyUI] 86%|████████▌ | 43/50 [16:39<02:43, 23.43s/it]
[ComfyUI] 88%|████████▊ | 44/50 [17:03<02:20, 23.40s/it]
[ComfyUI] 90%|█████████ | 45/50 [17:26<01:56, 23.38s/it]
[ComfyUI] 92%|█████████▏| 46/50 [17:49<01:33, 23.37s/it]
[ComfyUI] 94%|█████████▍| 47/50 [18:13<01:10, 23.36s/it]
[ComfyUI] 96%|█████████▌| 48/50 [18:36<00:46, 23.36s/it]
[ComfyUI] 98%|█████████▊| 49/50 [18:59<00:23, 23.35s/it]
[ComfyUI] 100%|██████████| 50/50 [19:23<00:00, 23.35s/it]
[ComfyUI] 100%|██████████| 50/50 [19:23<00:00, 23.27s/it]
[ComfyUI] Allocated memory: memory=12.316 GB
[ComfyUI] Max allocated memory: max_memory=34.067 GB
[ComfyUI] Max reserved memory: max_reserved=43.438 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,  1.49s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.26s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.30s/it]
[ComfyUI]
[ComfyUI] Blending tiles:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 28.49it/s]
[ComfyUI]
[ComfyUI] Decoding rows:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows:  50%|█████     | 1/2 [00:01<00:01,  1.48s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.26s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.29s/it]
[ComfyUI]
[ComfyUI] Blending tiles:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 25.60it/s]
[ComfyUI] 
[ComfyUI] Decoding rows:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows:  50%|█████     | 1/2 [00:01<00:01,  1.48s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.25s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.29s/it]
[ComfyUI]
[ComfyUI] Blending tiles:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 25.60it/s]
[ComfyUI] 
[ComfyUI] Decoding rows:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows:  50%|█████     | 1/2 [00:01<00:01,  1.48s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.26s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.29s/it]
[ComfyUI]
[ComfyUI] Blending tiles:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 25.60it/s]
[ComfyUI]
[ComfyUI] Decoding rows:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows:  50%|█████     | 1/2 [00:01<00:01,  1.30s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.10s/it]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:02<00:00,  1.13s/it]
[ComfyUI]
[ComfyUI] Blending tiles:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Blending tiles: 100%|██████████| 2/2 [00:00<00:00, 30.60it/s]
[ComfyUI]
[ComfyUI] Decoding rows:   0%|          | 0/2 [00:00<?, ?it/s]
[ComfyUI] Decoding rows:  50%|█████     | 1/2 [00:00<00:00,  4.43it/s]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00,  5.88it/s]
[ComfyUI] Decoding rows: 100%|██████████| 2/2 [00:00<00:00,  5.60it/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, 41.80it/s]
[ComfyUI] Prompt executed in 1201.26 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
90cb7cd3f846c48f7efbc2743a97aa56e44c2f3ee2c6bbbc3639929d8405ab09
Version Created
February 16, 2025
Run on Replicate →