The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Commits on master
fix: use Parameter assignment for Stable_Zero123 cc_projection weights (fixes #13492) (#13518)
cc6f950 Octopus committed 7 months ago
feat: RIFE and FILM frame interpolation model support (CORE-29) (#13258)
db85cf0 Jukka Seppänen committed 7 months ago
fix(veo): reject 4K resolution for veo-3.0 models in Veo3VideoGenerationNode (#13504)
91e1f45 Matt Miller committed 7 months ago
[Partner Nodes] added 4K resolution for Veo models; added Veo 3 Lite model (#13330)
1e1d4f1 Alexander Piskun committed 7 months ago
feat(api-nodes): add automatic downscaling of videos for ByteDance 2 nodes (#13465)
b38dd0f Alexander Piskun committed 7 months ago
fix: pin SQLAlchemy>=2.0 in requirements.txt (fixes #13036) (#13316)
543e9fb Octopus committed 7 months ago
fix: append directory type annotation to internal files endpoint response (#13078) (#13305)
138571d Abdul Rehman committed 7 months ago
Some optimizations to make Ernie inference a bit faster. (#13472)
3d816db comfyanonymous committed 7 months ago
fix(api-nodes): make "obj" output optional in Hunyuan3D Text and Image to 3D (#13449)
9635c2e Alexander Piskun committed 7 months ago
feat(api-nodes): add new "arrow-1.1" and "arrow-1.1-max" SVG models (#13447)
4f48be4 Alexander Piskun committed 7 months ago
fix(api-nodes): corrected StabilityAI price badges (#13454)
541fd10 Alexander Piskun committed 7 months ago
nodes_textgen: Implement use_default_template for LTX (#13451)
05f7531 rattus committed 7 months ago
feat(api-nodes): add 1080p resolution for SeeDance 2.0 model (#13437)
d0c53c5 Alexander Piskun committed 7 months ago
Add a way to disable default template in text gen node. (#13424)
e9a2d1e comfyanonymous committed 7 months ago
Fix OOM regression in _apply() for quantized models during inference (#13372)
1de83f9 Jun Yamog committed 7 months ago