lucataco/hunyuan-steamboat-willie – Run with an API on Replicate

lucataco / hunyuan-steamboat-willie

HunyuanVideo finetune of Walt Disney's: 1928 Steamboat Willie

Cold

Public
76 runs
H100
Fine-tune

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

In the style of SWR. A black and white animated scene featuring a mouse, dressed in a sailor outfit. The mouse is standing at the helm of a ship, holding the steering wheel with both hands.In the style of SWR. A black and white animated scene featuring a mouse, dressed in a sailor outfit. The mouse is standing at the helm of a ship, holding the steering wheel with both hands.

The text prompt describing your video scene.

Default: ""

lora_url

string

Shift + Return to add a new line

A URL pointing to your LoRA .safetensors file or a Hugging Face repo (e.g. 'user/repo' - uses the first .safetensors file).

Default: ""

lora_strength

number

(minimum: -10, maximum: 10)

Scale/strength for your LoRA.

Default: 1

scheduler

string

Algorithm used to generate the video frames.

Default: "DPMSolverMultistepScheduler"

steps

integer

(minimum: 1, maximum: 150)

Number of diffusion steps.

Default: 50

guidance_scale

number

(minimum: 0, maximum: 30)

Overall influence of text vs. model.

Default: 6

flow_shift

integer

(minimum: 0, maximum: 20)

Video continuity factor (flow).

Default: 9

num_frames

integer

(minimum: 1, maximum: 1440)

How many frames (duration) in the resulting video.

Default: 33

width

integer

(minimum: 64, maximum: 1536)

Width for the generated video.

Default: 640

height

integer

(minimum: 64, maximum: 1024)

Height for the generated video.

Default: 360

denoise_strength

number

(minimum: 0, maximum: 2)

Controls how strongly noise is applied each step.

Default: 1

force_offload

boolean

Whether to force model layers offloaded to CPU.

Default: true

frame_rate

integer

(minimum: 1, maximum: 60)

Video frame rate.

Default: 16

crf

integer

(minimum: 0, maximum: 51)

CRF (quality) for H264 encoding. Lower values = higher quality.

Default: 19

enhance_weight

number

(minimum: 0, maximum: 2)

Strength of the video enhancement effect.

Default: 0.3

enhance_single

boolean

Apply enhancement to individual frames.

Default: true

enhance_double

boolean

Apply enhancement across frame pairs.

Default: true

enhance_start

number

(minimum: 0, maximum: 1)

When to start enhancement in the video. Must be less than enhance_end.

Default: 0

enhance_end

number

(minimum: 0, maximum: 1)

When to end enhancement in the video. Must be greater than enhance_start.

Default: 1

seed

integer

Set a seed for reproducibility. Random by default.

Run this model in Node.js with one line of code:

npx create-replicate --model=lucataco/hunyuan-steamboat-willie

or set up a project from scratch

Install Replicate’s Node.js client library

npm install replicate

Set the REPLICATE_API_TOKEN environment variable

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run lucataco/hunyuan-steamboat-willie using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/hunyuan-steamboat-willie:6edfb0911970aed873d8783c8e118cbb6c8d06fb944d99331c6063ffed6d5831",
  {
    input: {
      crf: 19,
      steps: 50,
      width: 960,
      height: 544,
      prompt: "In the style of SWR. A black and white animated scene featuring a mouse, dressed in a sailor outfit. The mouse is standing at the helm of a ship, holding the steering wheel with both hands.",
      lora_url: "",
      scheduler: "DPMSolverMultistepScheduler",
      flow_shift: 9,
      frame_rate: 24,
      num_frames: 49,
      enhance_end: 1,
      enhance_start: 0,
      force_offload: true,
      lora_strength: 0.9,
      enhance_double: true,
      enhance_single: true,
      enhance_weight: 0.3,
      guidance_scale: 6,
      denoise_strength: 1
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library

pip install replicate

Set the REPLICATE_API_TOKEN environment variable

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client

import replicate

Run lucataco/hunyuan-steamboat-willie using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/hunyuan-steamboat-willie:6edfb0911970aed873d8783c8e118cbb6c8d06fb944d99331c6063ffed6d5831",
    input={
        "crf": 19,
        "steps": 50,
        "width": 960,
        "height": 544,
        "prompt": "In the style of SWR. A black and white animated scene featuring a mouse, dressed in a sailor outfit. The mouse is standing at the helm of a ship, holding the steering wheel with both hands.",
        "lora_url": "",
        "scheduler": "DPMSolverMultistepScheduler",
        "flow_shift": 9,
        "frame_rate": 24,
        "num_frames": 49,
        "enhance_end": 1,
        "enhance_start": 0,
        "force_offload": True,
        "lora_strength": 0.9,
        "enhance_double": True,
        "enhance_single": True,
        "enhance_weight": 0.3,
        "guidance_scale": 6,
        "denoise_strength": 1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run lucataco/hunyuan-steamboat-willie using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "6edfb0911970aed873d8783c8e118cbb6c8d06fb944d99331c6063ffed6d5831",
    "input": {
      "crf": 19,
      "steps": 50,
      "width": 960,
      "height": 544,
      "prompt": "In the style of SWR. A black and white animated scene featuring a mouse, dressed in a sailor outfit. The mouse is standing at the helm of a ship, holding the steering wheel with both hands.",
      "lora_url": "",
      "scheduler": "DPMSolverMultistepScheduler",
      "flow_shift": 9,
      "frame_rate": 24,
      "num_frames": 49,
      "enhance_end": 1,
      "enhance_start": 0,
      "force_offload": true,
      "lora_strength": 0.9,
      "enhance_double": true,
      "enhance_single": true,
      "enhance_weight": 0.3,
      "guidance_scale": 6,
      "denoise_strength": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2025-01-11T07:21:49.513351Z",
  "created_at": "2025-01-11T07:16:42.864000Z",
  "data_removed": false,
  "error": null,
  "id": "tgz5kyq6y1rmc0cmagw92ctftm",
  "input": {
    "crf": 19,
    "steps": 50,
    "width": 960,
    "height": 544,
    "prompt": "In the style of SWR. A black and white animated scene featuring a mouse, dressed in a sailor outfit. The mouse is standing at the helm of a ship, holding the steering wheel with both hands.",
    "lora_url": "",
    "flow_shift": 9,
    "frame_rate": 24,
    "num_frames": 49,
    "force_offload": true,
    "lora_strength": 0.9,
    "guidance_scale": 6,
    "denoise_strength": 1
  },
  "logs": "Random seed set to: 332011597\nChecking inputs\n====================================\nChecking weights\n✅ hunyuan_video_720_fp8_e4m3fn.safetensors exists in ComfyUI/models/diffusion_models\n✅ hunyuan_video_vae_bf16.safetensors exists in ComfyUI/models/vae\n====================================\nRunning workflow\n[ComfyUI] got prompt\nExecuting node 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode\n[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 43\n[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 44\n[ComfyUI] Input (height, width, video_length) = (544, 960, 49)\nExecuting node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler\n[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 50 inference steps\n[ComfyUI]\n[ComfyUI] 0%|          | 0/50 [00:00<?, ?it/s]\n[ComfyUI] 2%|▏         | 1/50 [00:04<03:16,  4.00s/it]\n[ComfyUI] 4%|▍         | 2/50 [00:09<03:55,  4.90s/it]\n[ComfyUI] 6%|▌         | 3/50 [00:15<04:03,  5.19s/it]\n[ComfyUI] 8%|▊         | 4/50 [00:20<04:04,  5.32s/it]\n[ComfyUI] 10%|█         | 5/50 [00:26<04:02,  5.40s/it]\n[ComfyUI] 12%|█▏        | 6/50 [00:31<03:59,  5.45s/it]\n[ComfyUI] 14%|█▍        | 7/50 [00:37<03:55,  5.48s/it]\n[ComfyUI] 16%|█▌        | 8/50 [00:42<03:50,  5.49s/it]\n[ComfyUI] 18%|█▊        | 9/50 [00:48<03:45,  5.50s/it]\n[ComfyUI] 20%|██        | 10/50 [00:53<03:40,  5.51s/it]\n[ComfyUI] 22%|██▏       | 11/50 [00:59<03:35,  5.52s/it]\n[ComfyUI] 24%|██▍       | 12/50 [01:04<03:29,  5.52s/it]\n[ComfyUI] 26%|██▌       | 13/50 [01:10<03:24,  5.52s/it]\n[ComfyUI] 28%|██▊       | 14/50 [01:15<03:18,  5.52s/it]\n[ComfyUI] 30%|███       | 15/50 [01:21<03:13,  5.52s/it]\n[ComfyUI] 32%|███▏      | 16/50 [01:26<03:07,  5.53s/it]\n[ComfyUI] 34%|███▍      | 17/50 [01:32<03:02,  5.53s/it]\n[ComfyUI] 36%|███▌      | 18/50 [01:38<02:56,  5.53s/it]\n[ComfyUI] 38%|███▊      | 19/50 [01:43<02:51,  5.53s/it]\n[ComfyUI] 40%|████      | 20/50 [01:49<02:45,  5.53s/it]\n[ComfyUI] 42%|████▏     | 21/50 [01:54<02:40,  5.53s/it]\n[ComfyUI] 44%|████▍     | 22/50 [02:00<02:34,  5.53s/it]\n[ComfyUI] 46%|████▌     | 23/50 [02:05<02:29,  5.53s/it]\n[ComfyUI] 48%|████▊     | 24/50 [02:11<02:23,  5.53s/it]\n[ComfyUI] 50%|█████     | 25/50 [02:16<02:18,  5.53s/it]\n[ComfyUI] 52%|█████▏    | 26/50 [02:22<02:12,  5.53s/it]\n[ComfyUI] 54%|█████▍    | 27/50 [02:27<02:07,  5.53s/it]\n[ComfyUI] 56%|█████▌    | 28/50 [02:33<02:01,  5.53s/it]\n[ComfyUI] 58%|█████▊    | 29/50 [02:38<01:56,  5.53s/it]\n[ComfyUI] 60%|██████    | 30/50 [02:44<01:50,  5.53s/it]\n[ComfyUI] 62%|██████▏   | 31/50 [02:49<01:45,  5.53s/it]\n[ComfyUI] 64%|██████▍   | 32/50 [02:55<01:39,  5.53s/it]\n[ComfyUI] 66%|██████▌   | 33/50 [03:00<01:34,  5.53s/it]\n[ComfyUI] 68%|██████▊   | 34/50 [03:06<01:28,  5.53s/it]\n[ComfyUI] 70%|███████   | 35/50 [03:12<01:22,  5.53s/it]\n[ComfyUI] 72%|███████▏  | 36/50 [03:17<01:17,  5.53s/it]\n[ComfyUI] 74%|███████▍  | 37/50 [03:23<01:11,  5.53s/it]\n[ComfyUI] 76%|███████▌  | 38/50 [03:28<01:06,  5.53s/it]\n[ComfyUI] 78%|███████▊  | 39/50 [03:34<01:00,  5.53s/it]\n[ComfyUI] 80%|████████  | 40/50 [03:39<00:55,  5.53s/it]\n[ComfyUI] 82%|████████▏ | 41/50 [03:45<00:49,  5.53s/it]\n[ComfyUI] 84%|████████▍ | 42/50 [03:50<00:44,  5.53s/it]\n[ComfyUI] 86%|████████▌ | 43/50 [03:56<00:38,  5.53s/it]\n[ComfyUI] 88%|████████▊ | 44/50 [04:01<00:33,  5.53s/it]\n[ComfyUI] 90%|█████████ | 45/50 [04:07<00:27,  5.53s/it]\n[ComfyUI] 92%|█████████▏| 46/50 [04:12<00:22,  5.53s/it]\n[ComfyUI] 94%|█████████▍| 47/50 [04:18<00:16,  5.53s/it]\n[ComfyUI] 96%|█████████▌| 48/50 [04:23<00:11,  5.53s/it]\n[ComfyUI] 98%|█████████▊| 49/50 [04:29<00:05,  5.53s/it]\n[ComfyUI] 100%|██████████| 50/50 [04:34<00:00,  5.53s/it]\n[ComfyUI] 100%|██████████| 50/50 [04:34<00:00,  5.50s/it]\n[ComfyUI] Allocated memory: memory=12.301 GB\n[ComfyUI] Max allocated memory: max_memory=18.380 GB\n[ComfyUI] Max reserved memory: max_reserved=20.250 GB\nExecuting node 5, title: HunyuanVideo Decode, class type: HyVideoDecode\n[ComfyUI]\n[ComfyUI] Decoding rows:   0%|          | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Decoding rows:  33%|███▎      | 1/3 [00:01<00:03,  1.50s/it]\n[ComfyUI] Decoding rows:  67%|██████▋   | 2/3 [00:03<00:01,  1.63s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00,  1.41s/it]\n[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00,  1.46s/it]\n[ComfyUI]\n[ComfyUI] Blending tiles:   0%|          | 0/3 [00:00<?, ?it/s]\n[ComfyUI] Blending tiles:  33%|███▎      | 1/3 [00:00<00:00,  7.33it/s]\nExecuting node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine\n[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 17.12it/s]\n[ComfyUI] Prompt executed in 296.05 seconds\noutputs:  {'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'}]}}\n====================================\nHunyuanVideo_00001.png\nHunyuanVideo_00001.mp4",
  "metrics": {
    "predict_time": 306.642053333,
    "total_time": 306.649351
  },
  "output": "https://replicate.delivery/xezq/oFhbE9LcewxsA6IjtDVJFDPhWVsvAHgZAZ6hOedAeqFaw5HoA/HunyuanVideo_00001.mp4",
  "started_at": "2025-01-11T07:16:42.871297Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-eevj7ogoztsh3oazz3s43znfzydbbo54md2jxpxemjge4t3muxga",
    "get": "https://api.replicate.com/v1/predictions/tgz5kyq6y1rmc0cmagw92ctftm",
    "cancel": "https://api.replicate.com/v1/predictions/tgz5kyq6y1rmc0cmagw92ctftm/cancel"
  },
  "version": "6edfb0911970aed873d8783c8e118cbb6c8d06fb944d99331c6063ffed6d5831"
}

Generated in

5 minutes 7 seconds

Tweak it ShareReport

Random seed set to: 332011597
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 30, title: HunyuanVideo TextEncode, class type: HyVideoTextEncode
[ComfyUI] llm prompt attention_mask shape: torch.Size([1, 161]), masked tokens: 43
[ComfyUI] clipL prompt attention_mask shape: torch.Size([1, 77]), masked tokens: 44
[ComfyUI] Input (height, width, video_length) = (544, 960, 49)
Executing node 3, title: HunyuanVideo Sampler, class type: HyVideoSampler
[ComfyUI] Sampling 49 frames in 13 latents at 960x544 with 50 inference steps
[ComfyUI]
[ComfyUI] 0%|          | 0/50 [00:00<?, ?it/s]
[ComfyUI] 2%|▏         | 1/50 [00:04<03:16,  4.00s/it]
[ComfyUI] 4%|▍         | 2/50 [00:09<03:55,  4.90s/it]
[ComfyUI] 6%|▌         | 3/50 [00:15<04:03,  5.19s/it]
[ComfyUI] 8%|▊         | 4/50 [00:20<04:04,  5.32s/it]
[ComfyUI] 10%|█         | 5/50 [00:26<04:02,  5.40s/it]
[ComfyUI] 12%|█▏        | 6/50 [00:31<03:59,  5.45s/it]
[ComfyUI] 14%|█▍        | 7/50 [00:37<03:55,  5.48s/it]
[ComfyUI] 16%|█▌        | 8/50 [00:42<03:50,  5.49s/it]
[ComfyUI] 18%|█▊        | 9/50 [00:48<03:45,  5.50s/it]
[ComfyUI] 20%|██        | 10/50 [00:53<03:40,  5.51s/it]
[ComfyUI] 22%|██▏       | 11/50 [00:59<03:35,  5.52s/it]
[ComfyUI] 24%|██▍       | 12/50 [01:04<03:29,  5.52s/it]
[ComfyUI] 26%|██▌       | 13/50 [01:10<03:24,  5.52s/it]
[ComfyUI] 28%|██▊       | 14/50 [01:15<03:18,  5.52s/it]
[ComfyUI] 30%|███       | 15/50 [01:21<03:13,  5.52s/it]
[ComfyUI] 32%|███▏      | 16/50 [01:26<03:07,  5.53s/it]
[ComfyUI] 34%|███▍      | 17/50 [01:32<03:02,  5.53s/it]
[ComfyUI] 36%|███▌      | 18/50 [01:38<02:56,  5.53s/it]
[ComfyUI] 38%|███▊      | 19/50 [01:43<02:51,  5.53s/it]
[ComfyUI] 40%|████      | 20/50 [01:49<02:45,  5.53s/it]
[ComfyUI] 42%|████▏     | 21/50 [01:54<02:40,  5.53s/it]
[ComfyUI] 44%|████▍     | 22/50 [02:00<02:34,  5.53s/it]
[ComfyUI] 46%|████▌     | 23/50 [02:05<02:29,  5.53s/it]
[ComfyUI] 48%|████▊     | 24/50 [02:11<02:23,  5.53s/it]
[ComfyUI] 50%|█████     | 25/50 [02:16<02:18,  5.53s/it]
[ComfyUI] 52%|█████▏    | 26/50 [02:22<02:12,  5.53s/it]
[ComfyUI] 54%|█████▍    | 27/50 [02:27<02:07,  5.53s/it]
[ComfyUI] 56%|█████▌    | 28/50 [02:33<02:01,  5.53s/it]
[ComfyUI] 58%|█████▊    | 29/50 [02:38<01:56,  5.53s/it]
[ComfyUI] 60%|██████    | 30/50 [02:44<01:50,  5.53s/it]
[ComfyUI] 62%|██████▏   | 31/50 [02:49<01:45,  5.53s/it]
[ComfyUI] 64%|██████▍   | 32/50 [02:55<01:39,  5.53s/it]
[ComfyUI] 66%|██████▌   | 33/50 [03:00<01:34,  5.53s/it]
[ComfyUI] 68%|██████▊   | 34/50 [03:06<01:28,  5.53s/it]
[ComfyUI] 70%|███████   | 35/50 [03:12<01:22,  5.53s/it]
[ComfyUI] 72%|███████▏  | 36/50 [03:17<01:17,  5.53s/it]
[ComfyUI] 74%|███████▍  | 37/50 [03:23<01:11,  5.53s/it]
[ComfyUI] 76%|███████▌  | 38/50 [03:28<01:06,  5.53s/it]
[ComfyUI] 78%|███████▊  | 39/50 [03:34<01:00,  5.53s/it]
[ComfyUI] 80%|████████  | 40/50 [03:39<00:55,  5.53s/it]
[ComfyUI] 82%|████████▏ | 41/50 [03:45<00:49,  5.53s/it]
[ComfyUI] 84%|████████▍ | 42/50 [03:50<00:44,  5.53s/it]
[ComfyUI] 86%|████████▌ | 43/50 [03:56<00:38,  5.53s/it]
[ComfyUI] 88%|████████▊ | 44/50 [04:01<00:33,  5.53s/it]
[ComfyUI] 90%|█████████ | 45/50 [04:07<00:27,  5.53s/it]
[ComfyUI] 92%|█████████▏| 46/50 [04:12<00:22,  5.53s/it]
[ComfyUI] 94%|█████████▍| 47/50 [04:18<00:16,  5.53s/it]
[ComfyUI] 96%|█████████▌| 48/50 [04:23<00:11,  5.53s/it]
[ComfyUI] 98%|█████████▊| 49/50 [04:29<00:05,  5.53s/it]
[ComfyUI] 100%|██████████| 50/50 [04:34<00:00,  5.53s/it]
[ComfyUI] 100%|██████████| 50/50 [04:34<00:00,  5.50s/it]
[ComfyUI] Allocated memory: memory=12.301 GB
[ComfyUI] Max allocated memory: max_memory=18.380 GB
[ComfyUI] Max reserved memory: max_reserved=20.250 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,  1.50s/it]
[ComfyUI] Decoding rows:  67%|██████▋   | 2/3 [00:03<00:01,  1.63s/it]
[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00,  1.41s/it]
[ComfyUI] Decoding rows: 100%|██████████| 3/3 [00:04<00:00,  1.46s/it]
[ComfyUI]
[ComfyUI] Blending tiles:   0%|          | 0/3 [00:00<?, ?it/s]
[ComfyUI] Blending tiles:  33%|███▎      | 1/3 [00:00<00:00,  7.33it/s]
Executing node 34, title: Video Combine 🎥🅥🅗🅢, class type: VHS_VideoCombine
[ComfyUI] Blending tiles: 100%|██████████| 3/3 [00:00<00:00, 17.12it/s]
[ComfyUI] Prompt executed in 296.05 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

Examples

View more examples

Run time and cost

This model runs on Nvidia H100 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

About

Fine-tune of Walt Disney’s 1928 Steamboat Willie featuring Mickey Mouse

Follow me on Twitter/X @lucataco93

Process

Take a 10 second video and split it up into 2 second segments with: lucataco/video-split
Take the video segments and create captions with: lucataco/qwen2-vl-7b-instruct
Train with this model: HunyuanVideo finetuner