Skip to content

New HunyuanVideo-I2V #11066

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Mar 24, 2025
Merged

New HunyuanVideo-I2V #11066

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
5da0839
update
a-r-r-o-w Mar 15, 2025
af24bea
update
a-r-r-o-w Mar 17, 2025
85fc267
Merge branch 'main' into integrations/hunyuan-video-i2v-new
a-r-r-o-w Mar 19, 2025
2846939
update
a-r-r-o-w Mar 19, 2025
4a0481e
add tests
a-r-r-o-w Mar 20, 2025
7b8dd64
update docs
a-r-r-o-w Mar 20, 2025
5c63cc0
Merge branch 'main' into integrations/hunyuan-video-i2v-new
a-r-r-o-w Mar 20, 2025
720519d
raise value error
a-r-r-o-w Mar 20, 2025
028a965
warning for true cfg and guidance scale
a-r-r-o-w Mar 20, 2025
c4c359e
Merge branch 'main' into integrations/hunyuan-video-i2v-new
a-r-r-o-w Mar 21, 2025
1ac2057
fix test
a-r-r-o-w Mar 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion docs/source/en/api/pipelines/hunyuan_video.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,8 @@ The following models are available for the image-to-video pipeline:
| Model name | Description |
|:---|:---|
| [`Skywork/SkyReels-V1-Hunyuan-I2V`](https://huggingface.co/Skywork/SkyReels-V1-Hunyuan-I2V) | Skywork's custom finetune of HunyuanVideo (de-distilled). Performs best with `97x544x960` resolution. Performs best at `97x544x960` resolution, `guidance_scale=1.0`, `true_cfg_scale=6.0` and a negative prompt. |
| [`hunyuanvideo-community/HunyuanVideo-I2V`](https://huggingface.co/hunyuanvideo-community/HunyuanVideo-I2V) | Tecent's official HunyuanVideo I2V model. Performs best at resolutions of 480, 720, 960, 1280. A higher `shift` value when initializing the scheduler is recommended (good values are between 7 and 20) |
| [`hunyuanvideo-community/HunyuanVideo-I2V-33ch`](https://huggingface.co/hunyuanvideo-community/HunyuanVideo-I2V) | Tecent's official HunyuanVideo 33-channel I2V model. Performs best at resolutions of 480, 720, 960, 1280. A higher `shift` value when initializing the scheduler is recommended (good values are between 7 and 20). |
| [`hunyuanvideo-community/HunyuanVideo-I2V`](https://huggingface.co/hunyuanvideo-community/HunyuanVideo-I2V) | Tecent's official HunyuanVideo 16-channel I2V model. Performs best at resolutions of 480, 720, 960, 1280. A higher `shift` value when initializing the scheduler is recommended (good values are between 7 and 20) |

## Quantization

Expand Down
23 changes: 22 additions & 1 deletion scripts/convert_hunyuan_video_to_diffusers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,8 +160,9 @@ def remap_single_transformer_blocks_(key, state_dict):
"pooled_projection_dim": 768,
"rope_theta": 256.0,
"rope_axes_dim": (16, 56, 56),
"image_condition_type": None,
},
"HYVideo-T/2-I2V": {
"HYVideo-T/2-I2V-33ch": {
"in_channels": 16 * 2 + 1,
"out_channels": 16,
"num_attention_heads": 24,
Expand All @@ -178,6 +179,26 @@ def remap_single_transformer_blocks_(key, state_dict):
"pooled_projection_dim": 768,
"rope_theta": 256.0,
"rope_axes_dim": (16, 56, 56),
"image_condition_type": "latent_concat",
},
"HYVideo-T/2-I2V-16ch": {
"in_channels": 16,
"out_channels": 16,
"num_attention_heads": 24,
"attention_head_dim": 128,
"num_layers": 20,
"num_single_layers": 40,
"num_refiner_layers": 2,
"mlp_ratio": 4.0,
"patch_size": 2,
"patch_size_t": 1,
"qk_norm": "rms_norm",
"guidance_embeds": True,
"text_embed_dim": 4096,
"pooled_projection_dim": 768,
"rope_theta": 256.0,
"rope_axes_dim": (16, 56, 56),
"image_condition_type": "token_replace",
},
}

Expand Down
Loading
Loading