diffusers

diffusers copied to clipboard

Vague error: `ValueError: With local_files_only set to False, you must first locally save the tokenizer in the following path: 'openai/clip-vit-large-patch14'.` how to fix?

11

Trying to convert a .safetensors stable diffusion model to whatever the format is that hugging face requires. It throws a vague nonsequitur of an error: `pipe = diffusers.StableDiffusionPipeline.from_single_file(str(aPathlibPath/"vodkaByFollowfoxAI_v40.safetensors") )` ```......

openSourcerer9000

fix AnimateDiff creation with a unet loaded with IP Adapter

2

# What does this PR do? Makes it possible to load a pipeline with an IP Adapter into an AnimateDiff pipeline with from_pipe() Fixes #7661 - Pipelines: @sayakpaul @yiyixuxu @DN6

fabiorigano

Added get_velocity function to EulerDiscreteScheduler.

15

# What does this PR do? This PR adds the get_velocity function to EulerDiscreteScheduler, which is needed for training/fine-tuning with this scheduler if the `prediction_type` is `v_prediction`. Fixes #6359 ##...

RuiningLi

[WIP] DragNUWA SVD

4

# What does this PR do? Code: https://github.com/ProjectNUWA/DragNUWA Paper: https://arxiv.org/abs/2308.08089 Project Page: https://www.microsoft.com/en-us/research/project/dragnuwa/ Demo: https://huggingface.co/spaces/yinsming/DragNUWA Fixes #6497. This is a WIP and I've freely made changes to the unet code,...

a-r-r-o-w

[Dreambooth LoRA training] Add `edm` tags + scheduler type to model card

3

- Add `edm-training` tag to canonical and advanced dreambooth lora training scripts when EDM style training is used - Add scheduler type to model card for inference with EDM schedulers

linoytsaban

Set main_input_name in StableDiffusionSafetyChecker to "clip_input"

5

FlaxStableDiffusionSafetyChecker sets main_input_name to "clip_input". This makes StableDiffusionSafetyChecker consistent.

clinty

Enhance Documentation with Google Style Docstrings for Export Methods in utils

3

This PR adds Google style docstrings to export functions (buffered_writer, export_to_gif, export_to_ply, export_to_obj, export_to_video), enhancing documentation clarity and developer understanding. I was working with export_to_video method and I had to...

hamza-m-farooqi

NotImplementedError: Cannot copy out of meta tensor; no data! coz, Some weights of the model checkpoint were not used when initializing CLIPTextModelWithProjection

13

### Describe the bug I try to load a .safetensors file and save it as diffusers type model and I got **Some weights of the model checkpoint were not used...

shabri-arrahim

adapt masked im2im pipeline for SDXL

3

Implement sketch inpaint from a1111 for non-inpaint models. This PR implement the same algorithm as here for https://github.com/huggingface/diffusers/pull/4824 but this pipeline has more parameters

noskill

[mps] training / inferencing deepfloyd must be done in float32

3

### Describe the bug _**Just to keep track of this issue, because I'm not sure if I've done something wrong or if it's due to the current issues in Pytorch's...

bghira