diffusers

diffusers copied to clipboard

Add training options

6

### Continue training existing model Modified train_unconditional so the model is reloaded if it exists: `export COMMAND="python examples/train_unconditional.py --resolution 32 --num_epochs 10 --train_data_dir training-images --output_dir model"` ``` % ${COMMAND} creating...

luckybit4755

Reduce Stable Diffusion memory usage by keeping unet only on GPU.

6

**Is your feature request related to a problem? Please describe.** Stable Diffusion is not compute heavy on all its steps. If we keep the diffusion unet on fp16 on GPU...

piEsposito

ValueError: The deprecation tuple ('tensor_format' ...

9

### Describe the bug I am getting the following error ``` ValueError: The deprecation tuple ('tensor_format', '0.5.0', "If you're running your code in PyTorch, you can safely remove this argument.")...

WASasquatch

[Feature Request] Dreambooth - Save intermediate checkpoints

1

**Is your feature request related to a problem? Please describe.** Dreambooth can drastically change its output quality between step counts, including to the worse if the chosen learning rate is...

DominikDoom

Optimize VRAM use in textual inversion training

19

Cast frozen modules to fp16/bf16 when using mixed precision. Add gradient checkpoint command line option. OOMs before on my 8 GB VRAM GPU. With these changes and using `--mixed_precision=fp16 --gradient_checkpointing`...

Ttl

Possible Apple MPS issue - prompts array fails to generate any images

7

### Describe the bug If you pass an array of prompts (a list of strings) rather than single prompt (a single string) to the pipeline, under Apple `mps` you never...

FahimF

train_unconditional.py fails on call to evaluate()

3

### Describe the bug On the first attempt to call `evaluate()` in the train_loop() function, the DDPMPipeline fails due to an incompatible output form the model. This raises an AttributeError:...

jdk514

'PNDMScheduler' object has no attribute 'set_format'

9

### Describe the bug Getting this error from pipeline_stable_diffusion.py ### Reproduction _No response_ ### Logs _No response_ ### System Info On colab notebook: https://colab.research.google.com/github/WASasquatch/easydiffusion/blob/main/Stability_AI_Easy_Diffusion.ipynb

jalexs82

Can't convert ckpt model to diffusers with convert_original_stable_diffusion_to_diffusers

2

### Describe the bug I have some ckpt files and try to convert it to diffusers in google colab. with this command `!python /content/diffusers/scripts/convert_original_stable_diffusion_to_diffusers.py --checkpoint_path /content/gdrive/MyDrive/Waifu_6e.ckpt --dump_path /content/stable-diffusion-alt` But got...

Desm0nt

CLIP model support for pipelines

1

I am not sure if this has been considered, or already on the roadmap, but I'd love to be able to just throw a CLIP model ID at a pipe...

WASasquatch