Fix: disable cache_examples to prevent OOM at startup on T4

Fix: move depth_anything to CPU to free VRAM for SDXL pipeline on T4

Fix: enable_model_cpu_offload to reduce VRAM usage on T4 GPU

Fix: restore original requirements.txt for Python 3.10

Fix: pin python_version to 3.10 for compatibility

Fix: upgrade diffusers>=0.31.0 to fix FLAX_WEIGHTS_NAME import error with transformers>=4.45.0

Fix: use transformers>=4.45.0 to support Python 3.13 (tokenizers compatibility)

Update requirements.txt

Update pipeline_stable_diffusion_xl_instantid_full.py

Update app.py

Update app.py

Update requirements.txt

Update requirements.txt

Update app.py

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update README.md

add spring festival style

use depth-anything

update

update

update

update

update

update

update

add pose examples

update

fix cuda errors

spaces

fix

fix

support lcm and multi-controlnets

Update README.md (#13)

Update README.md

Update README.md

add to negative prompt (#9)

Replace gr.Files with gr.Image (#8)

fix typo

add sort

revert

fix cache examples error (#4)

add cache

ZeroGPU (#3)

replace base

fix

Upload 4 files

update

update