huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
PythonApache-2.0
Pinned issues
Issues
- 0
`lora_scale` has no effect when loading with Flux
#9525 opened by cshowley - 0
- 2
UNetMotionModel.dtype is really expensive to call, is it possible to cache it during inference?
#9520 opened by xiang9156 - 10
- 0
- 1
parameters `joint_attention_kwargs` doesn't be passed to FLUX's transformers model
#9516 opened by HorizonWind2004 - 0
The `JointAttnProcessor2_0` in the `SD3Transformer2DModel` does not include `RMSNorm`.
#9515 opened by HuiZhang0812 - 1
- 2
train_dreambooth_lora_flux validation RuntimeError: Input type (float) and bias type (c10::BFloat16) should be the same
#9476 opened by squewel - 0
Multi-controlnet batching for `StableDiffusionXLControlNetInpaintPipeline`
#9511 opened by kdubovikov - 4
train_dreambooth_lora_flux with prodigy and train_text_encoder causes IndexError: list index out of range
#9464 opened by squewel - 12
[Schedulers] Add SGMUniform
#9416 opened by asomoza - 2
- 3
SD3ControlNetModel forward function error
#9496 opened by pibbo88 - 6
Dreambooth Flux training failed on saving a checkpoint
#9500 opened by kopyl - 3
Dreambooth Flux training error: RuntimeError: mat2 must be a matrix, got 1-D tensor
#9497 opened by kopyl - 0
AnimateDiff SparseCtrl RGB does not work as expected
#9508 opened by a-r-r-o-w - 2
Can't upscale anything. Keep getting "KeyError: 'middle_block_out.0.weight'" error/
#9505 opened by evanerichards - 6
Remove redundant comparison inside the diffusion loop of stable video diffusion pipeline
#9425 opened by dianyo - 4
- 1
FLUX dreambooth train on multigpu with deepspeed
#9484 opened by zhangvia - 0
- 4
ValueError: Multiple file extensions found at ./models/coreml-stable-diffusion-v1-4_original_packages.Cannot infer resource type from contents.
#9471 opened by LukeLIN-web - 2
SDXL PAG with IPAdapter is not working.
#9495 opened by akshatd007 - 4
Lumina pipeline fails to generate any image
#9488 opened by zhuole1025 - 8
FluxPipeline - Multi-GPU Issue - When you define transformer= you get "Expected all tensors to be on the same device"
#9450 opened by CrackerHax - 1
Add FLUX image-to-image to `AutoPipelineForImage2Image`
#9492 opened by apolinario - 8
Problem with FluxInpaintPipeline when doing a replace.
#9486 opened by ukaprch - 3
Add GGUF loader for FluxTransformer2DModel
#9487 opened by vladmandic - 2
Prompt scheduling in Diffusers like A1111
#9470 opened by linhbeige - 0
- 1
[BUG] 'GatheredParameters' object is not callable
#9477 opened by LinB203 - 3
Formulation of reverse diffusion process in DDPM ( 1 - alpha_prod_t = beta_prod_t assumption)
#9474 opened by jadevaibhav - 9
- 3
- 3
CogVideoX I2V: Missing guard-rail on num_frames
#9467 opened by tin2tin - 3
Flux inference og
#9461 opened by echosyy - 3
AttributeError: 'tuple' object has no attribute 'shape' while using IP-Adapter with StableDiffusionControlNetInpaintPipeline
#9448 opened by satvik-pyxer - 2
CogVideoX Image2Video model not found
#9454 opened by rolux - 1
Enable assigning a list of SD3ControlNetModel to StableDiffusion3ControlNetPipeline
#9460 opened by avrech - 1
[BUG] SNR gamma in v_prediction
#9451 opened by LinB203 - 3
model_name in quicktour page results in a 404 error
#9438 opened by vinayakkgarg - 1
- 4
Suggestion for speeding up `index_for_timestep` by removing sequential `nonzero()` calls in samplers
#9417 opened by ethanweber - 3
- 0
AttributeError: 'NoneType' object has no attribute 'get'
#9430 opened by molo32 - 7
d3_dreambooth_lora_16gb.ipynb broken for me with latest, ok with released version
#9424 opened by 3a1b2c3 - 5
A strange thing happened when I wrote my own code to train Cotrolnet_sdxl, as soon as I did the first backpropagation, noise_pred became nan.
#9422 opened by Li-Zn-H - 2
add new parameter module of CogVideoXTransformer3DModel, raise error
#9415 opened by trouble-maker007 - 1
CogvideoX-5b adds freeze-frames in start and end of clip
#9413 opened by tin2tin