automatic/TODO.md

TODO

Main ToDo list can be found at GitHub projects

Current

Future Candidates

• Refactor: Move model_* stuff into subfolder
• Refactor: sampler options
• Common repo for T5 and CLiP
• Upgrade: unblock numpy: see gradio
• Upgrade: unblock pydantic: see https://github.com/Cschlaefli/automatic

Complete Features

• Python==3.13 improved support
• Video: API support
• LoRA: add OMI format support for SD35/FLUX.1

Under Consideration

• IPAdapter negative guidance
• IPAdapter composition
• Refactor attention
• STG
• LBM
• SmoothCache
• MagCache
• HiDream GGUF
• Diffusers guiders
• Nunchaku PulID
• Dream0 guidance
• S3Diff diffusion upscaler
• SUPIR upscaler

Monitoring

• TensorRT

New models

Stable

• Diffusers-0.34.0
• WanAI-2.1 VACE(https://github.com/huggingface/diffusers/pull/11582)
• LTXVideo-0.9.7(https://github.com/huggingface/diffusers/pull/11516)
• Cosmos-Predict2-Video(https://github.com/huggingface/diffusers/pull/11695)

Pending

• Magi(https://github.com/huggingface/diffusers/pull/11713)
• SEVA
• SkyReels-v2(https://github.com/huggingface/diffusers/pull/11518)

External:Unified/MultiModal

• Bagel(https://github.com/bytedance-seed/bagel)
• Ming
• Liquid

External:Image2Image/Editing

• Step1X
• SD3 UltraEdit

External:Video

• WAN2GP
• SelfForcing
• DiffusionForcing
• LanDiff
• HunyuanCustom
• HunyuanAvatar
• WAN-CausVid
• WAN-CausVid-Plus t2v
• WAN-StepDistill

Code TODO

pnpm lint | grep W0511 | awk -F'TODO ' '{print "- "$NF}' | sed 's/ (fixme)//g'

• control: support scripts via api
• fc: autodetect distilled based on model
• fc: autodetect tensor format based on model
• hypertile: vae breaks when using non-standard sizes
• install: enable ROCm for windows when available
• loader: load receipe
• loader: save receipe
• lora: add other quantization types
• lora: add t5 key support for sd35/f1
• lora: maybe force imediate quantization
• model load: force-reloading entire model as loading transformers only leads to massive memory usage
• model loader: implement model in-memory caching
• modernui: monkey-patch for missing tabs.select event
• modules/lora/lora_extract.py:188:9: W0511: TODO: lora: support pre-quantized flux
• nunchaku: batch support
• nunchaku: cache-dir for transformer and t5 loader
• processing: remove duplicate mask params
• resize image: enable full VAE mode for resize-latent