Skip to content

Hunyuan Video Framepack #11428

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 23 commits into from
May 6, 2025
Merged

Hunyuan Video Framepack #11428

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
23 commits
Select commit Hold shift + click to select a range
6c86a3d
add transformer
a-r-r-o-w Apr 27, 2025
6bafea7
Merge branch 'main' into integrations/framepack
linoytsaban Apr 28, 2025
5a523cd
add pipeline
a-r-r-o-w Apr 28, 2025
e2fde45
fixes
a-r-r-o-w Apr 28, 2025
ea7e3cd
make fix-copies
a-r-r-o-w Apr 28, 2025
ee54a19
update
a-r-r-o-w Apr 29, 2025
f0d286b
add flux mu shift
a-r-r-o-w Apr 29, 2025
6e1b557
update example snippet
a-r-r-o-w Apr 29, 2025
88e8dd3
debug
a-r-r-o-w Apr 29, 2025
65c24f6
cleanup
a-r-r-o-w Apr 29, 2025
68a7fa6
batch_size=1 optimization
a-r-r-o-w Apr 29, 2025
8df1710
add pipeline test
a-r-r-o-w Apr 29, 2025
4221738
Merge branch 'main' into integrations/framepack
linoytsaban Apr 29, 2025
ccf593e
fix for model cpu offloading'
a-r-r-o-w Apr 29, 2025
0070763
add last_image support; credits: https://github.com/lllyasviel/FrameP…
a-r-r-o-w Apr 29, 2025
5567118
update example with flf2v
a-r-r-o-w Apr 29, 2025
dbe378d
update penguin url
a-r-r-o-w Apr 29, 2025
1c1c2c0
fix test
a-r-r-o-w Apr 29, 2025
668c0b2
Merge branch 'main' into integrations/framepack
linoytsaban Apr 30, 2025
2f9efa9
address review comment: https://github.com/huggingface/diffusers/pull…
a-r-r-o-w May 5, 2025
17a57b2
address review comment: https://github.com/huggingface/diffusers/pull…
a-r-r-o-w May 5, 2025
7bcaae0
Merge branch 'main' into integrations/framepack
a-r-r-o-w May 5, 2025
e959a40
Update src/diffusers/pipelines/hunyuan_video/pipeline_hunyuan_video_f…
a-r-r-o-w May 6, 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
1 change: 1 addition & 0 deletions 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 @@ -52,6 +52,7 @@ The following models are available for the image-to-video pipeline:
| [`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-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) |
- [`lllyasviel/FramePackI2V_HY`](https://huggingface.co/lllyasviel/FramePackI2V_HY) | lllyasviel's paper introducing a new technique for long-context video generation called [Framepack](https://arxiv.org/abs/2504.12626). |

## Quantization

Expand Down
4 changes: 4 additions & 0 deletions src/diffusers/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -175,6 +175,7 @@
"HunyuanDiT2DControlNetModel",
"HunyuanDiT2DModel",
"HunyuanDiT2DMultiControlNetModel",
"HunyuanVideoFramepackTransformer3DModel",
"HunyuanVideoTransformer3DModel",
"I2VGenXLUNet",
"Kandinsky3UNet",
Expand Down Expand Up @@ -376,6 +377,7 @@
"HunyuanDiTPAGPipeline",
"HunyuanDiTPipeline",
"HunyuanSkyreelsImageToVideoPipeline",
"HunyuanVideoFramepackPipeline",
"HunyuanVideoImageToVideoPipeline",
"HunyuanVideoPipeline",
"I2VGenXLPipeline",
Expand Down Expand Up @@ -770,6 +772,7 @@
HunyuanDiT2DControlNetModel,
HunyuanDiT2DModel,
HunyuanDiT2DMultiControlNetModel,
HunyuanVideoFramepackTransformer3DModel,
HunyuanVideoTransformer3DModel,
I2VGenXLUNet,
Kandinsky3UNet,
Expand Down Expand Up @@ -950,6 +953,7 @@
HunyuanDiTPAGPipeline,
HunyuanDiTPipeline,
HunyuanSkyreelsImageToVideoPipeline,
HunyuanVideoFramepackPipeline,
HunyuanVideoImageToVideoPipeline,
HunyuanVideoPipeline,
I2VGenXLPipeline,
Expand Down
2 changes: 2 additions & 0 deletions src/diffusers/models/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,7 @@
_import_structure["transformers.transformer_flux"] = ["FluxTransformer2DModel"]
_import_structure["transformers.transformer_hidream_image"] = ["HiDreamImageTransformer2DModel"]
_import_structure["transformers.transformer_hunyuan_video"] = ["HunyuanVideoTransformer3DModel"]
_import_structure["transformers.transformer_hunyuan_video_framepack"] = ["HunyuanVideoFramepackTransformer3DModel"]
_import_structure["transformers.transformer_ltx"] = ["LTXVideoTransformer3DModel"]
_import_structure["transformers.transformer_lumina2"] = ["Lumina2Transformer2DModel"]
_import_structure["transformers.transformer_mochi"] = ["MochiTransformer3DModel"]
Expand Down Expand Up @@ -156,6 +157,7 @@
FluxTransformer2DModel,
HiDreamImageTransformer2DModel,
HunyuanDiT2DModel,
HunyuanVideoFramepackTransformer3DModel,
HunyuanVideoTransformer3DModel,
LatteTransformer3DModel,
LTXVideoTransformer3DModel,
Expand Down
1 change: 1 addition & 0 deletions src/diffusers/models/transformers/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
from .transformer_flux import FluxTransformer2DModel
from .transformer_hidream_image import HiDreamImageTransformer2DModel
from .transformer_hunyuan_video import HunyuanVideoTransformer3DModel
from .transformer_hunyuan_video_framepack import HunyuanVideoFramepackTransformer3DModel
from .transformer_ltx import LTXVideoTransformer3DModel
from .transformer_lumina2 import Lumina2Transformer2DModel
from .transformer_mochi import MochiTransformer3DModel
Expand Down
Loading