Skip to content

[Fix] chroma docs #12360

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
Sep 22, 2025
Merged

[Fix] chroma docs #12360

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
10a6230
Fixes chroma docs
SahilCarterr Sep 21, 2025
1637926
fix docs
SahilCarterr Sep 21, 2025
c039c94
Merge branch 'main' into chroma_docs
SahilCarterr Sep 22, 2025
1dba96c
Merge branch 'main' into chroma_docs
SahilCarterr Sep 22, 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
10 changes: 5 additions & 5 deletions src/diffusers/pipelines/chroma/pipeline_chroma.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -688,11 +688,11 @@ def __call__(
their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
will be used.
guidance_scale (`float`, *optional*, defaults to 3.5):
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this should be 5.0 (same for the im2img pipeline)?

diffusers/src/diffusers/pipelines/chroma/pipeline_chroma.py

Line 649 in 5796735

guidance_scale: float = 5.0,

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actually, where is the source that says chroma's default cfg should be 5.0? The comfyui recommended workflow seems to say it should be 4.0, meanwhile I had always thought that 3.5 was the correct default value.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pinging @Ednaordinary who would know better since they implemented the pipeline :)

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

both lodestones/Chroma1-Base and lodestones/Chroma1-HD have 3.0 in their readme example, though anywhere between 3 and 4 should be fine! thanks for the ping

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Then cfg 3.5 is fine . Thanks @Ednaordinary and @mingyi456

Embedded guiddance scale is enabled by setting `guidance_scale` > 1. Higher `guidance_scale` encourages
a model to generate images more aligned with `prompt` at the expense of lower image quality.

Guidance-distilled models approximates true classifer-free guidance for `guidance_scale` > 1. Refer to
the [paper](https://huggingface.co/papers/2210.03142) to learn more.
Guidance scale as defined in [Classifier-Free Diffusion
Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
of [Imagen Paper](https://huggingface.co/papers/2205.11487). Guidance scale is enabled by setting
`guidance_scale > 1`. Higher guidance scale encourages to generate images that are closely linked to
the text `prompt`, usually at the expense of lower image quality.
num_images_per_prompt (`int`, *optional*, defaults to 1):
The number of images to generate per prompt.
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
Expand Down
12 changes: 6 additions & 6 deletions src/diffusers/pipelines/chroma/pipeline_chroma_img2img.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -749,12 +749,12 @@ def __call__(
Custom sigmas to use for the denoising process with schedulers which support a `sigmas` argument in
their `set_timesteps` method. If not defined, the default behavior when `num_inference_steps` is passed
will be used.
guidance_scale (`float`, *optional*, defaults to 5.0):
Embedded guiddance scale is enabled by setting `guidance_scale` > 1. Higher `guidance_scale` encourages
a model to generate images more aligned with `prompt` at the expense of lower image quality.

Guidance-distilled models approximates true classifer-free guidance for `guidance_scale` > 1. Refer to
the [paper](https://huggingface.co/papers/2210.03142) to learn more.
guidance_scale (`float`, *optional*, defaults to 3.5):
Guidance scale as defined in [Classifier-Free Diffusion
Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2.
of [Imagen Paper](https://huggingface.co/papers/2205.11487). Guidance scale is enabled by setting
`guidance_scale > 1`. Higher guidance scale encourages to generate images that are closely linked to
the text `prompt`, usually at the expense of lower image quality.
strength (`float, *optional*, defaults to 0.9):
Conceptually, indicates how much to transform the reference image. Must be between 0 and 1. image will
be used as a starting point, adding more noise to it the larger the strength. The number of denoising
Expand Down