Search results

Ideogram4: Ideogram4MRoPE breaks under torch.autocast: all image positions collapse, producing flat single-color images

bugSomething isn't workingSomething isn't working

models

Status: Open.

#13920 In huggingface/diffusers;

· dxqb opened on Jun 11, 2026

[New Pipeline/Model] Add JoyAI-Echo multi-shot audio-video generation pipeline

feature-request

models

pipelines

Status: Open.

#13909 In huggingface/diffusers;

· sjq66 opened on Jun 10, 2026

[Anima] Add img2img capability

contributions-welcome

feature-request

good first issueGood for newcomersGood for newcomers

modular-pipelines

Status: Open.

#13903 In huggingface/diffusers;

· asomoza opened on Jun 9, 2026

When use UniPCMultistepScheduler as the ODE solver, and input different num_inference_steps in StableDiffusionXLPipeline, the first inference step is wrong

bugSomething isn't workingSomething isn't working

needs-code-exampleWaiting for relevant code example to be providedWaiting for relevant code example to be provided

pipelines

schedulers

Status: Open.

#13887 In huggingface/diffusers;

· TheLovesOfLadyPurple opened on Jun 8, 2026

docs: fix typos in scheduling_euler_discrete.py

bugSomething isn't workingSomething isn't working

needs-code-exampleWaiting for relevant code example to be providedWaiting for relevant code example to be provided

schedulers

Status: Open.

#13877 In huggingface/diffusers;

· ramkumar27072006 opened on Jun 7, 2026

fix underlying issue with test_from_save_pretrained_dtype_inference is that the model.to(dtype) cast at

Status: Open.

#13869 In huggingface/diffusers;

· sayakpaul opened on Jun 5, 2026

flux2-klein lora train，bug

bugSomething isn't workingSomething isn't working

lora

needs-code-exampleWaiting for relevant code example to be providedWaiting for relevant code example to be provided

pipelines

Status: Open.

#13866 In huggingface/diffusers;

· lspze opened on Jun 4, 2026

[<languageCode>] Translating docs to <languageName>

feature-request

Status: Open.

#13858 In huggingface/diffusers;

· borisdavalosp opened on Jun 3, 2026

[Community Support] Integrating visual generative foundation models in diffusers

Status: Open.

#13844 In huggingface/diffusers;

· Bili-Sakura opened on May 30, 2026

Fix incorrect batch handling in _prepare_image_ids usage in train_dreambooth_lora_flux2_img2img.py

bugSomething isn't workingSomething isn't working

Status: Open.

#13811 In huggingface/diffusers;

· Zhu1116 opened on May 26, 2026

Incompatibility between FlashAttention and ERNIE Image

bugSomething isn't workingSomething isn't working

pipelines

Status: Open.

#13801 In huggingface/diffusers;

· SamuelTallet opened on May 24, 2026

Support for Stable Audio 3 Medium

feature-request

pipelines

Status: Open.

#13793 In huggingface/diffusers;

· sdevil7th opened on May 22, 2026