stduhpf 4513e3fda9 refactor: img-cond->img_uncond (#1594) ...

* refactor: img-cond->img_uncond

* align APG and CFG++ with img-uncond CFG

* set default img_cfg to 1.f

---------

Co-authored-by: leejet <leejet714@gmail.com>

2026-06-03 22:57:42 +08:00

..

model_io

feat: support safetensors export in convert mode (#1444)

2026-04-20 00:22:11 +08:00

tokenizers

feat: add PiD support (#1585)

2026-05-31 22:38:39 +08:00

anima.hpp

refactor: simplify diffusion model runner params (#1569)

2026-05-28 00:12:35 +08:00

auto_encoder_kl.hpp

feat: add Longcat-Image / Longcat-Image-Edit support (#1053)

2026-05-24 02:02:02 +08:00

cache_dit.hpp

refactor: migrate generation pipeline to sd::Tensor (#1373)

2026-03-30 00:19:25 +08:00

clip.hpp

feat: add module backend assignment support (#1500)

2026-05-16 20:27:06 +08:00

common_block.hpp

feat: transition from compile-time to runtime backend discovery (#1448)

2026-04-29 23:26:57 +08:00

common_dit.hpp

feat: add ltx2.3 support (#1463)

2026-05-17 16:46:20 +08:00

condition_cache_utils.hpp

refactor: migrate generation pipeline to sd::Tensor (#1373)

2026-03-30 00:19:25 +08:00

conditioner.hpp

feat: --stream-layers for streaming weights from CPU during generation (#1576)

2026-06-02 22:35:28 +08:00

control.hpp

fix: prevent crash in case of a mem alloc error and graceful exit (#1566)

2026-05-30 18:34:07 +08:00

convert.cpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

denoiser.hpp

feat: add support for APG (adaptive projected guidance) + unconditionnal SLG (#593)

2026-06-01 00:55:49 +08:00

diffusion_model.hpp

refactor: simplify diffusion model runner params (#1569)

2026-05-28 00:12:35 +08:00

easycache.hpp

refactor: migrate generation pipeline to sd::Tensor (#1373)

2026-03-30 00:19:25 +08:00

ernie_image.hpp

refactor: simplify diffusion model runner params (#1569)

2026-05-28 00:12:35 +08:00

esrgan.hpp

fix: prevent crash in case of a mem alloc error and graceful exit (#1566)

2026-05-30 18:34:07 +08:00

flux.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

ggml_extend_backend.cpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

ggml_extend_backend.h

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

ggml_extend.hpp

feat: --stream-layers for streaming weights from CPU during generation (#1576)

2026-06-02 22:35:28 +08:00

ggml_graph_cut.cpp

feat: --stream-layers for streaming weights from CPU during generation (#1576)

2026-06-02 22:35:28 +08:00

ggml_graph_cut.h

feat: --stream-layers for streaming weights from CPU during generation (#1576)

2026-06-02 22:35:28 +08:00

gits_noise.inl

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00

guidance.cpp

refactor: img-cond->img_uncond (#1594)

2026-06-03 22:57:42 +08:00

guidance.h

refactor: img-cond->img_uncond (#1594)

2026-06-03 22:57:42 +08:00

hidream_o1.hpp

fix: prevent crash in case of a mem alloc error and graceful exit (#1566)

2026-05-30 18:34:07 +08:00

latent-preview.h

feat: add ltxav latent2rgb projection matrix (#1502)

2026-05-17 17:52:05 +08:00

layer_registry.cpp

feat: --stream-layers for streaming weights from CPU during generation (#1576)

2026-06-02 22:35:28 +08:00

layer_registry.h

feat: --stream-layers for streaming weights from CPU during generation (#1576)

2026-06-02 22:35:28 +08:00

lens.hpp

refactor: simplify diffusion model runner params (#1569)

2026-05-28 00:12:35 +08:00

llm.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

lora.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

ltx_audio_vae.h

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

ltx_latent_upscaler.hpp

feat: add LTX temporal latent upscaler support (#1551)

2026-05-23 01:35:13 +08:00

ltx_vae.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

ltxv.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

mmdit.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

model.cpp

feat: add PiD support (#1585)

2026-05-31 22:38:39 +08:00

model.h

feat: add PiD support (#1585)

2026-05-31 22:38:39 +08:00

name_conversion.cpp

fix: resolve LLM norm tensor names by architecture (#1570)

2026-05-28 00:36:16 +08:00

name_conversion.h

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00

ordered_map.hpp

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00

pid.hpp

feat: add PiD support (#1585)

2026-05-31 22:38:39 +08:00

pmid.hpp

fix: prevent crash in case of a mem alloc error and graceful exit (#1566)

2026-05-30 18:34:07 +08:00

preprocessing.hpp

perf: speed up tensor_to_sd_image conversion (#1466)

2026-04-30 01:13:56 +08:00

qwen_image.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

rng_mt19937.hpp

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00

rng_philox.hpp

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00

rng.hpp

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00

rope.hpp

feat: add PiD support (#1585)

2026-05-31 22:38:39 +08:00

sample-cache.cpp

refactor: migrate generation pipeline to sd::Tensor (#1373)

2026-03-30 00:19:25 +08:00

sample-cache.h

refactor: migrate generation pipeline to sd::Tensor (#1373)

2026-03-30 00:19:25 +08:00

spectrum.hpp

refactor: migrate generation pipeline to sd::Tensor (#1373)

2026-03-30 00:19:25 +08:00

stable-diffusion.cpp

refactor: img-cond->img_uncond (#1594)

2026-06-03 22:57:42 +08:00

t5.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

tae.hpp

fix: correct tae for models that use the flux2 vae (#1571)

2026-05-28 09:13:16 +08:00

tensor_ggml.hpp

feat: add ltx2.3 support (#1463)

2026-05-17 16:46:20 +08:00

tensor.hpp

feat: add support for APG (adaptive projected guidance) + unconditionnal SLG (#593)

2026-06-01 00:55:49 +08:00

ucache.hpp

refactor: migrate generation pipeline to sd::Tensor (#1373)

2026-03-30 00:19:25 +08:00

unet.hpp

refactor: simplify diffusion model runner params (#1569)

2026-05-28 00:12:35 +08:00

upscaler.cpp

feat: --stream-layers for streaming weights from CPU during generation (#1576)

2026-06-02 22:35:28 +08:00

upscaler.h

feat: --stream-layers for streaming weights from CPU during generation (#1576)

2026-06-02 22:35:28 +08:00

util.cpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

util.h

feat: add Longcat-Image / Longcat-Image-Edit support (#1053)

2026-05-24 02:02:02 +08:00

vae.hpp

Feat: Temporal tile custom size with overlap (#1510)

2026-05-21 23:44:12 +08:00

version.cpp

refactor: reorganize the file structure (#1266)

2026-02-10 23:13:35 +08:00

wan.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00

z_image.hpp

refactor: call CPU backend functions dynamically (#1591)

2026-06-01 23:41:21 +08:00