Skip to content

[Single File] Add GGUF support for LTX #10298

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 4 commits into from
Dec 20, 2024
Merged

[Single File] Add GGUF support for LTX #10298

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f55c584
update
DN6 Dec 19, 2024
f5fc22e
Merge branch 'main' into ltx-gguf
sayakpaul Dec 19, 2024
f5272ea
Merge branch 'main' into ltx-gguf
sayakpaul Dec 20, 2024
5d7d8e7
add docs.
sayakpaul Dec 20, 2024
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
15 changes: 7 additions & 8 deletions src/diffusers/loaders/single_file_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,10 +99,11 @@
"model.diffusion_model.double_blocks.0.img_attn.norm.key_norm.scale",
],
"ltx-video": [
(
"model.diffusion_model.patchify_proj.weight",
"model.diffusion_model.transformer_blocks.27.scale_shift_table",
),
"model.diffusion_model.patchify_proj.weight",
"model.diffusion_model.transformer_blocks.27.scale_shift_table",
"patchify_proj.weight",
"transformer_blocks.27.scale_shift_table",
"vae.per_channel_statistics.mean-of-means",
],
"autoencoder-dc": "decoder.stages.1.op_list.0.main.conv.conv.bias",
"autoencoder-dc-sana": "encoder.project_in.conv.bias",
Expand Down Expand Up @@ -601,7 +602,7 @@ def infer_diffusers_model_type(checkpoint):
else:
model_type = "flux-schnell"

elif any(all(key in checkpoint for key in key_list) for key_list in CHECKPOINT_KEY_NAMES["ltx-video"]):
elif any(key in checkpoint for key in CHECKPOINT_KEY_NAMES["ltx-video"]):
model_type = "ltx-video"

elif CHECKPOINT_KEY_NAMES["autoencoder-dc"] in checkpoint:
Expand Down Expand Up @@ -2266,9 +2267,7 @@ def swap_scale_shift(weight):


def convert_ltx_transformer_checkpoint_to_diffusers(checkpoint, **kwargs):
converted_state_dict = {
key: checkpoint.pop(key) for key in list(checkpoint.keys()) if "model.diffusion_model." in key
}
converted_state_dict = {key: checkpoint.pop(key) for key in list(checkpoint.keys()) if "vae" not in key}

TRANSFORMER_KEYS_RENAME_DICT = {
"model.diffusion_model.": "",
Expand Down
Loading