diffusers

diffusers copied to clipboard

[SD3] pipe.enable_xformers_memory_efficient_attention

13

### Describe the bug > RuntimeError: The size of tensor a (154) must match the size of tensor b (2304) at non-singleton dimension 1 ### Reproduction ```python # StableDiffusion3Pipeline pipe.enable_xformers_memory_efficient_attention()...

CanvaChen

controlnet++

2

### Model/Pipeline/Scheduler description https://huggingface.co/huchenlei/ControlNet_plus_plus_collection_fp16/tree/main https://huggingface.co/huchenlei/ControlNet_plus_plus_collection_fp16/discussions/1 ``` Traceback (most recent call last): File "/home/zznet/workspace/ai-pipe/prod-ai-pipe-replace-model/runpod_app.py", line 14, in from pipe import text2img, getText2imgPipe, set_sampler, compel File "/home/zznet/workspace/ai-pipe/prod-ai-pipe-replace-model/pipe.py", line 17, in canny_control =...

crapthings

Stable Cascade Controlnet training

4

**Is your feature request related to a problem? Please describe.** Last year I wrote [a long article on how to train controlnets](https://civitai.com/articles/2078) using diffusers, and trained [two](https://civitai.com/models/137638) [controlnets](civitai.com/models/149740) using diffusers....

geroldmeisinger

IndexError: index 29 is out of bounds for dimension 0 with size 29

6

### Describe the bug I have three problems because of the same reason. 1) TypeError: unsupported operand type(s) for +=: 'NoneType' and 'int' # upon completion increase step index by...

Anvarka

refactor SD3, speedup tests

4

# What does this PR do? - Refactor some of the SD3 modeling implementation. Accessing configuration parameters in `__init__` via the config attribute is not necessary or clean. Can use...

a-r-r-o-w

make `single_file` tests device-agnostic

1

# What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks...

faaany

Unexpected behavior of `image_processor.apply_overlay`

11

### Describe the bug The `apply_overlay` method of `image_processor` works unexpectedly if `init_image` and `image` have different shapes. For example it can appear using `StableDiffusionXLInpaintPipeline` with `padding_mask_crop` value filled. According...

cortwave

[core] Mochi T2V

1

Fixes #9744 Github: https://github.com/genmoai/models Model: https://huggingface.co/genmo/mochi-1-preview

a-r-r-o-w

text_input_ids_list not part of encode_prompt definition

1

Description code is trying to pass `text_input_ids_list` as argument for `encode_prompt`, but, `text_input_ids_list` isn't supposed to be part of argument as per the definition. Call https://github.com/huggingface/diffusers/blob/298ab6eb01f3ef475c15218ea87de1494e1250aa/examples/dreambooth/train_dreambooth_sd3.py#L1597-L1601 Definition for `encode_prompt` https://github.com/huggingface/diffusers/blob/298ab6eb01f3ef475c15218ea87de1494e1250aa/examples/dreambooth/train_dreambooth_sd3.py#L900-L976...

Vatsal-Malaviya

[Flux IPadapter] Support Xlabs IPadapter in diffusers

8

It'd be great to have XLabs IPadapter supported in diffusers. Code: https://github.com/XLabs-AI/x-flux/ Checkpoint: https://huggingface.co/XLabs-AI/flux-ip-adapter/tree/main @sayakpaul

chuck-ma