Chroma as a FLUX.1 variant #11566
Draft
Chroma as a FLUX.1 variant #11566
+273
−25
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Hi, is there a specific model repo this works with. I'm getting key errors loading the models from lodestones/Chroma and silveroxides/Chroma-GGUF PR installed by using $ pip uninstall diffusers
$ pip install git+https://github.com/huggingface/diffusers.git@refs/pull/11566/merge
$ grep chroma lib/python3.11/site-packages/diffusers/models/transformers/transformer_flux.py
INVALID_VARIANT_ERRMSG = "`variant` must be `'flux' or `'chroma'`."
elif variant == "chroma":
elif variant == "chroma":
elif variant == "chroma":
norm_out_cls = AdaLayerNormContinuous if variant != "chroma" else AdaLayerNormContinuousPruned
is_chroma = isinstance(self.time_text_embed, CombinedTimestepTextProjChromaEmbeddings)
if not is_chroma:
if is_chroma:
if is_chroma:
if is_chroma:
I'm loading the models using #ckpt_path="/Volumes/SSD2TB/AI/caches/models/chroma-unlocked-v29-Q8_0.gguf"
ckpt_path="/Volumes/SSD2TB/AI/caches/models/chroma-unlocked-v29.5.safetensors"
transformer = FluxTransformer2DModel.from_single_file(
ckpt_path,
# quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
torch_dtype=torch.bfloat16,
variant="chroma"
)The full error is.... Traceback (most recent call last):
File "/Volumes/SSD2TB/AI/Diffusers/gguf_chroma.py", line 48, in <module>
transformer = FluxTransformer2DModel.from_single_file(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Volumes/SSD2TB/AI/Diffusers/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/Volumes/SSD2TB/AI/Diffusers/lib/python3.11/site-packages/diffusers/loaders/single_file_model.py", line 370, in from_single_file
diffusers_format_checkpoint = checkpoint_mapping_fn(
^^^^^^^^^^^^^^^^^^^^^^
File "/Volumes/SSD2TB/AI/Diffusers/lib/python3.11/site-packages/diffusers/loaders/single_file_utils.py", line 2157, i
8EE0
n convert_flux_transformer_checkpoint_to_diffusers
converted_state_dict["time_text_embed.timestep_embedder.linear_1.weight"] = checkpoint.pop(
^^^^^^^^^^^^^^^
KeyError: 'time_in.in_layer.weight' |
|
This is still Draft. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Fixes # (issue)
Before submitting
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.