Spaces:
Running on Zero
Running on Zero
Commit History
-
Fix blocky/checkerboard artifacts: pass kv_cache=True so reference (pose) tokens use isolated attention as this LoRA was trained (matches ComfyUI Krea2OstrisEditModelPatch kv_cache=True) Running
Verified signature9f21968 -
Fix blocky/checkerboard artifacts: deterministic VAE reference-latent encode (posterior mode) matching ComfyUI, instead of stochastic latent_dist.sample()
Verified signature2840c9e -
Docs: reflect FluxKontextImageScale bucket sizing
Verified signatured120fe8 -
Fix pose fidelity/quality: replicate ComfyUI FluxKontextImageScale (nearest ~1MP bucket + center-crop + Lanczos) for pose sizing so ref-latent grid == output grid at native ~1MP resolution
Verified signature42ff634 -
Match ComfyUI workflow: guidance_scale=0 (cfg=1/no-CFG on Turbo), single LoRA scaling, aspect-preserving <=1MP /16 sizing
Verified signaturec1cad15
-
Add matplotlib (needed by controlnet_aux detect_poses)
Verified signature0ac4d97 -
Move theme/css to launch() per Gradio 6
Verified signature26cff59 -
Document two input modes + resolution-matching fix
Verified signaturef33061d -
Add opencv-python for pose rendering
Verified signature6ad3c2f -
Match output size to pose for stronger control + add interactive pose-editing (Pose Image / Regular Image tabs)
Verified signature65ff002 -
Upload app.py with huggingface_hub
Verified signature839f769 -
Upload folder using huggingface_hub
Verified signaturec15b3c0 -
initial commit
Verified signature0a77289