9 Commits

Author	SHA1	Message	Date
nolan4	b222265628	qwen eligen batch size > 1 fix	2025-10-24 19:22:26 -07:00
nolan4	b0ade4bb85	mask instead of image inputs for qwen eligen pipeline	2025-10-24 18:22:39 -07:00
nolan4	0f4a141faf	working using comfyUI's optimized attention and rotary embedding funcs	2025-10-24 17:37:26 -07:00
nolan4	1d9124203f	fixed application of entity-specific RoPE embeddings	2025-10-23 22:56:32 -07:00
nolan4	ffe3503370	appearing functional without rigorous testing	2025-10-22 22:20:43 -07:00
Alexander Piskun	160698eb41	convert nodes_qwen.py to V3 schema (#10049)	2025-09-27 12:25:35 -07:00
comfyanonymous	1fee8827cb	Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus. (#9986)	2025-09-22 16:49:48 -04:00
comfyanonymous	bddd69618b	Change the TextEncodeQwenImageEdit node to use logic closer to reference. (#9432)	2025-08-19 16:49:01 -04:00
comfyanonymous	4977f203fa	P2 of qwen edit model. (#9412) ... * P2 of qwen edit model. * Typo. * Fix normal qwen. * Fix. * Make the TextEncodeQwenImageEdit also set the ref latent. If you don't want it to set the ref latent and want to use the ReferenceLatent node with your custom latent instead just disconnect the VAE.	2025-08-18 22:38:34 -04:00