Hawk Lee
ae68afdd41
fix(teacache): restore missing skip_flag definition
2026-01-20 01:33:05 +08:00
Hawk Lee
c3dca9c4dc
fix(teacache): force calc on first step
2026-01-20 01:28:13 +08:00
Hawk Lee
36936ff7c7
chore(cleanup): remove debug prints from solver
2026-01-20 01:11:01 +08:00
Hawk Lee
baa794ea1a
fix(pipeline): prioritize transformer device for execution
2026-01-20 01:06:43 +08:00
Hawk Lee
5af1fa4e4d
fix(pipeline): force latents to transformer device in __call__
2026-01-20 01:02:00 +08:00
Hawk Lee
225f4d3466
fix(pipeline): force prepare_latents to use transformer device
2026-01-20 00:57:45 +08:00
Hawk Lee
c5906bc6b4
chore(debug): add debug prints to pipeline
2026-01-20 00:56:29 +08:00
Hawk Lee
8e05fcac31
chore(debug): add debug prints to solver
2026-01-20 00:46:20 +08:00
Hawk Lee
5da29b5c4b
fix(scheduler): force sigma_t to sample device
2026-01-20 00:41:25 +08:00
Hawk Lee
a41c65bcaf
fix(scheduler): move sigmas to correct device
2026-01-20 00:31:10 +08:00
Hawk Lee
efc42867ff
fix(transformer): fix device mismatch in time_embedding
2026-01-20 00:23:49 +08:00
Hawk Lee
895981804a
chore: remove debug prints
2026-01-20 00:17:41 +08:00
Hawk Lee
31c7b08a6b
fix(wan): ensure input tensor is on correct device in patch_embed
2026-01-20 00:08:37 +08:00
Hawk Lee
53ac7dc881
fix(wan): disable autocast for patch_embedding
2026-01-20 00:06:04 +08:00
Hawk Lee
5254567c32
fix(wan): force F.conv3d with explicit float32 weights
2026-01-20 00:03:18 +08:00
Hawk Lee
fa50a5dae2
fix(transformer): use in-place float32 conversion for patch_embedding
2026-01-19 23:43:44 +08:00
Hawk Lee
f1848bb81a
fix(transformer): disable autocast for forced float32 conv3d
2026-01-19 23:38:14 +08:00
Hawk Lee
67cc60515b
fix(transformer): force patch_embedding to float32
2026-01-19 23:33:20 +08:00
Hawk Lee
09292cb631
fix(transformer): add .contiguous() to patch_embedding input
2026-01-19 23:26:04 +08:00
Hawk Lee
ccd416ad2a
fix(pipeline): ensure correct device usage in loop
2026-01-19 23:22:18 +08:00
Hawk Lee
7c14df3fbe
fix(pipeline): fix indentation bug in prepare_mask_latents
2026-01-19 23:13:29 +08:00
Hawk Lee
220e1146b9
fix(echomimic): add .contiguous() to vae and move back to GPU
2026-01-19 23:10:12 +08:00
Hawk Lee
312aa234f0
feat(debug): add logging to VAE encoding loop
2026-01-19 23:08:33 +08:00
Hawk Lee
130ae46f86
fix(echomimic): run VAE on CPU to avoid cuda 3D conv error
2026-01-19 22:51:47 +08:00
Hawk Lee
5728e75829
fix(pipeline): add clip_context argument to __call__
2026-01-19 21:48:02 +08:00
Hawk Lee
317b693a4a
perf(echomimic): permit passing pre-computed clip_context to pipeline
2026-01-19 21:34:26 +08:00
Hawk Lee
741a95909a
fix(echomimic): handle missing text_encoder in pipeline to support memory optimization
2026-01-19 21:17:54 +08:00
Hawk Lee
cf0775785d
debug: add print statements to pipeline
2026-01-19 21:05:57 +08:00
Hawk Lee
cd701b0032
fix(echomimic): correct batch_size logic in pipeline __call__ method
2026-01-19 21:01:11 +08:00
Hawk Lee
d51c6c07e9
fix(echomimic): correct batch_size logic (take 2)
2026-01-19 20:50:46 +08:00
Hawk Lee
5f48fd666c
fix(echomimic): revert transpose and implement correct flat-list CFG
2026-01-19 20:41:19 +08:00
Hawk Lee
13708df19c
fix(echomimic): transpose T5 embeddings to Time-Major [S,B,D] for transformer
2026-01-19 20:31:36 +08:00
Hawk Lee
d624a8e06f
fix(echomimic): correct I2V context concatenation for 4D T5 layers
2026-01-19 20:26:04 +08:00
Hawk Lee
dd0a41ae72
fix(echomimic): correct CFG embedding concatenation for list inputs
2026-01-19 20:20:26 +08:00
Hawk Lee
e9e5141a0c
fix(echomimic): syntax error in pipeline
2026-01-19 20:10:13 +08:00
Hawk Lee
adb2e780d9
fix(echomimic): handle list-type prompt_embeds in encode_prompt
2026-01-19 20:09:55 +08:00
Hawk Lee
5aaf22b20a
fix(echomimic): handle list embeddings in pipeline and verbose memory cleanup
2026-01-19 20:00:52 +08:00
Hawk Lee
b9bd2cf65e
fix(echomimic): fallback to base model for missing components
2026-01-19 18:49:25 +08:00
Hawk Lee
f9cdac4414
fix(echomimic): update config subpaths to standard folder names
2026-01-19 18:46:48 +08:00
Hawk Lee
b4ca6d0d35
docs(echomimic): update model source to BadToBest/EchoMimicV3
2026-01-19 18:39:39 +08:00
Hawk Lee
c580668329
fix(echomimic): disable TF gpu and use sequential offload
2026-01-19 18:18:37 +08:00
Hawk Lee
f45d3c0984
fix(echomimic): force add dist folder in new location
2026-01-19 17:42:13 +08:00
Hawk Lee
dc1acb8c0e
refactor(echomimic): rename src to echomimic_v3_src to avoid namespace collisions
2026-01-19 17:40:27 +08:00
Hawk Lee
d88eacc777
fix(echomimic): force add missing __init__.py
2026-01-19 17:38:16 +08:00
Hawk Lee
351111eeeb
fix: force add src/dist module
2026-01-19 17:24:58 +08:00
Hawk Lee
c9441f1b92
feat: add EchoMimic V3 nodes
2026-01-19 16:40:13 +08:00
Hawk Lee
7d8fe8ea4a
fix: Remove nested submodule references from libs/CosyVoice
...
- Removed libs/CosyVoice/third_party/Matcha-TTS/.git (gitfile)
- Removed libs/CosyVoice/.gitmodules
- This fixes 'no submodule mapping found' error in GitHub Actions
2026-01-06 20:01:17 +08:00
Hawk Lee
e76af6119e
fix: resolve submodule error by vendoring CosyVoice lib + bump version to 1.6.2
2026-01-04 23:41:10 +08:00
Hawk Lee
174cc81609
feat(podcast): Add VibeVoice Batch Modes and Fixes
...
- Add Batch Mode (Natural, Strict, Whole) to Dialogue TTS
- Fix VibeVoice trailing noise with auto-trim
- Fix built-in audio clipping by attenuating volume
- Add comment support to Script Parser
- Update README with new features
2026-01-04 20:27:06 +08:00
Hawk Lee