diffusers

diffusers copied to clipboard

Dance Diffusion in FP16

2

At the moment dance diffusion in FP16 seems to perform relatively bad even though it was trained in FP16 with AMP autocast -> the reason might just be because the...

patrickvonplaten

Training diffusers examples using torch FSDP

2

### Describe the bug I am able to run the current diffuser examples as specified in the readme steps https://github.com/huggingface/diffusers/tree/main/examples/text_to_image https://github.com/huggingface/diffusers/tree/main/examples/unconditional_image_generation Would like to know if the examples can be...

shrinath-suresh

Implement `add_noise` in iPNDMScheduler

1

This method is missing from the recently-added IPNDMScheduler. It's not required for inference, but I think we should add it for consistency with all the others. TODO: - [ ]...

pcuenca

When I use CLIPGuidedStableDiffusion based on stable-diffusion-2, the generated result is incredibly bad, all mosaic.

2

### Describe the bug When I use CLIPGuidedStableDiffusion based on stable-diffusion-2, the generated result is incredibly bad, all mosaic.  ### Reproduction from diffusers import DiffusionPipeline from transformers import CLIPFeatureExtractor,...

ScottishFold007

Implement v-prediction in all schedulers

3

This would be nice to guarantee scheduler interoperability in Stable Diffusion 2. DDIM, DDPM and EulerDiscrete already support v-prediction, the following ones remain (from the list of compatible stable diffusion...

pcuenca

CPU offloading currently done in a hacky way.

1

### Describe the bug It seems like `accelerate` doesn't yet support cpu offloading of modules that have single parameters such as: https://github.com/huggingface/diffusers/blob/29021090614641d2509155ca0021497896228999/src/diffusers/pipelines/stable_diffusion/safety_checker.py#L44 which forces one to do the following: https://github.com/huggingface/diffusers/blob/2c6bc0f13ba2ba609ac141022b4b56b677d74943/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py#L238...

patrickvonplaten

Why does train_text_to_image.py perform so differently from the CompVis script?

12

I posted about this on the forum but didn't get any useful feedback - would love to hear from someone who knows the in and outs of the diffusers codebase!...

john-sungjin

[Feature Request][Community] Ability to pass text_embeddings/uncond_embeddings as arguments in pipe call

12

**Is your feature request related to a problem? Please describe.** Im experimenting with aesthetic gradients and need to overwrite pip call to pass text_embeddings/uncond_embeddings. Also it might save a bit...

hadaev8

Multiple prompts

8

### Model/Pipeline/Scheduler description Hi. How to use: from diffusers import FlaxStableDiffusionPipeline pipeline, params = FlaxStableDiffusionPipeline.from_pretrained( "runwayml/stable-diffusion-v1-5", revision="bf16", dtype=jax.numpy.bfloat16 ) to generate multiple prompts instead of single one (prompt = "a...

tralala87

Performance Issue with RTX 4090 and all SD/Diffusers versions

37

### Describe the bug Hello! Since 10 days, nearly round the clock, I try to bring my brand new and proudly owned Geforce RTX 4090 graphic cards to work appropriate...

Marcophono2