355 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
leejet	c47affcd59	update docs	2025-10-13 23:13:12 +08:00
leejet	4edc3ad2ad	to_out.0 precision fix	2025-10-13 23:02:24 +08:00
leejet	162d5cef64	Merge branch 't5_fix' into qwen_image_edit	2025-10-13 00:04:58 +08:00
leejet	17f012556b	remove dup line	2025-10-12 23:56:33 +08:00
leejet	74e020efee	Merge branch 'master' into t5_fix	2025-10-12 23:54:18 +08:00
Wagner Bruna	9727c6bb98	fix: resolve VAE tiling problem in Qwen Image (#873) master-319-9727c6b	2025-10-12 23:45:53 +08:00
leejet	beb99a2de2	feat: add Qwen Image support (#851) ... * add qwen tokenizer * add qwen2.5 vl support * mv qwen.hpp -> qwenvl.hpp * add qwen image model * add qwen image t2i pipeline * fix qwen image flash attn * add qwen image i2i pipline * change encoding of vocab_qwen.hpp to utf8 * fix get_first_stage_encoding * apply jeffbolz f32 patch https://github.com/leejet/stable-diffusion.cpp/pull/851#issuecomment-3335515302 * fix the issue that occurs when using CUDA with k-quants weights * optimize the handling of the FeedForward precision fix * to_add_out precision fix * update docs master-318-beb99a2	2025-10-12 23:23:19 +08:00
Wagner Bruna	aa68b875b9	refactor: deal with default img-cfg-scale at the library level (#869) master-317-aa68b87	2025-10-12 23:17:52 +08:00
Wagner Bruna	5b261b9cee	feat: add a stand-alone upscale mode (#865) ... * feat: add a stand-alone upscale mode * fix prompt option check * format code * update README.md --------- Co-authored-by: leejet <leejet714@gmail.com> master-316-5b261b9	2025-10-12 23:10:02 +08:00
Pedrito	e70d0205ca	feat: add support for more esrgan models & x2 & x1 models (#855) master-315-e70d020	2025-10-12 22:53:31 +08:00
leejet	ca14940869	T5DenseGatedActDense precision fix	2025-10-12 18:52:45 +08:00
leejet	d21d1aa830	update docs	2025-10-12 18:11:56 +08:00
leejet	b4b5b4c153	Merge branch 'qwen_image' into qwen_image_edit	2025-10-12 17:29:04 +08:00
leejet	7519e2f11a	to_add_out precision fix	2025-10-12 17:27:51 +08:00
leejet	0741f1405f	Merge branch 'qwen_image' into qwen_image_edit	2025-10-12 16:47:15 +08:00
leejet	cc064a0530	optimize the handling of the FeedForward precision fix	2025-10-12 16:36:55 +08:00
leejet	98d6e71492	fix the issue that occurs when using CUDA with k-quants weights	2025-10-12 15:41:40 +08:00
leejet	47c0f8e4bd	set prompt_template_encode_start_idx every time	2025-10-12 00:51:36 +08:00
leejet	b769da2faf	Merge branch 'qwen_image' into qwen_image_edit	2025-10-11 01:06:12 +08:00
leejet	6ea2a75929	apply jeffbolz f32 patch ... https://github.com/leejet/stable-diffusion.cpp/pull/851#issuecomment-3335515302	2025-10-11 01:04:14 +08:00
leejet	d19d4a5903	Merge branch 'master' into qwen_image	2025-10-11 00:52:20 +08:00
leejet	02af48a97f	chore: fix vulkan ci (#878) master-314-02af48a	2025-10-11 00:40:57 +08:00
leejet	e12d5e0aaf	fix: ensure directory iteration results are sorted by filename (#858)	2025-10-11 00:18:39 +08:00
Serkan Sahin	940a2018e1	chore: fix dockerfile libgomp1 dependency + improvements (#852)	2025-10-11 00:17:45 +08:00
Sharuzzaman Ahmat Raslan	b451728b2f	docs: update README.md (#866)	2025-10-11 00:11:10 +08:00
stduhpf	11f436c483	feat: add support for Flux Controls and Flex.2 (#692)	2025-10-11 00:06:57 +08:00
leejet	70654d004d	revert Rope::gen_qwen_image_ids	2025-10-10 22:29:14 +08:00
leejet	a123e25ae8	support dynamic number of Qwen image transformer blocks	2025-10-10 21:49:09 +08:00
leejet	9fa817f014	add mmproj file support	2025-10-10 01:09:05 +08:00
leejet	887055edce	fix qwen image edit pipeline	2025-10-09 01:37:52 +08:00
leejet	40752b629f	add qwen image edit support	2025-10-08 19:51:15 +08:00
leejet	58e81adf61	add qwen2vl vit support	2025-09-29 23:05:30 +08:00
leejet	95cae28465	optimize clip_preprocess and fix get_first_stage_encoding	2025-09-25 23:30:21 +08:00
leejet	4e48e6b82b	add ref latent support for qwen image	2025-09-25 23:30:21 +08:00
leejet	94f4f295c1	Merge branch 'master' into qwen_image	2025-09-25 23:13:00 +08:00
leejet	35843c77ea	fix: optimize the handling of embedding weight (#859) master-309-35843c7	2025-09-25 23:09:59 +08:00
leejet	178a415d89	Merge branch 'master' into qwen_image	2025-09-25 22:01:08 +08:00
leejet	6ad46bb700	sync: update ggml	2025-09-25 21:57:43 +08:00
leejet	a3a2b2d721	fix get_first_stage_encoding	2025-09-25 00:41:56 +08:00
leejet	a8d3aa0415	Merge branch 'master' into qwen_image	2025-09-25 00:39:57 +08:00
leejet	1ba30ce005	sync: update ggml	2025-09-25 00:38:38 +08:00
leejet	2abe9451c4	fix: optimize the handling of CLIP embedding weight (#840) master-306-2abe945	2025-09-25 00:28:20 +08:00
Wagner Bruna	f3140eadbb	fix: tensor loading thread count (#854) master-305-f3140ea	2025-09-25 00:26:38 +08:00
Stefan-Olt	98ba155fc6	docs: HipBLAS / ROCm build instruction fix (#843)	2025-09-25 00:03:05 +08:00
Wagner Bruna	513f36d495	docs: include Vulkan compatibility for LoRA quants (#845)	2025-09-25 00:01:10 +08:00
rmatif	1e0d2821bb	fix: correct tensor deduplication logic (#844) master-302-1e0d282	2025-09-24 23:22:40 +08:00
leejet	5af0bb0aee	change encoding of vocab_qwen.hpp to utf8	2025-09-22 23:57:59 +08:00
leejet	feb027958f	add qwen image i2i pipline	2025-09-22 23:45:29 +08:00
leejet	477911fb20	fix qwen image flash attn	2025-09-22 22:19:03 +08:00
leejet	cf19c6e759	add qwen image t2i pipeline	2025-09-22 21:18:28 +08:00