Commits · d70b0bc43c2d1d0a2212e9493926ddf231c80a41 · chenpangpang / ComfyUI

"tests/git@developer.sourcefind.cn:xdb4_94051/vllm.git" did not exist on "e41f06702cb6d6787ac4474832264108a6e28780"

29 Aug, 2023 13 commits
- Use the GPU for the canny preprocessor when available. · d70b0bc4
  comfyanonymous authored Aug 29, 2023
  
  d70b0bc4
- Add node to convert a specific colour in an image to a mask. · 81d9200e
  comfyanonymous authored Aug 29, 2023
  
  81d9200e
- Support SDXL t2i adapters with 3 channel input. · f2f5e5dc
  comfyanonymous authored Aug 29, 2023
  
  f2f5e5dc
- Move beta_schedule to model_config and allow disabling unet creation. · 15adc369
  comfyanonymous authored Aug 29, 2023
  
  15adc369
- Merge branch 'feat/mute_bypass_nodes_in_group' of https://github.com/M1kep/ComfyUI · 968078b1
  comfyanonymous authored Aug 29, 2023
  
  968078b1
- Merge branch 'preserve-pnginfo' of https://github.com/chrisgoringe/ComfyUI · 66c690e6
  comfyanonymous authored Aug 29, 2023
  
  66c690e6
- Remove optimization that caused border. · bed116a1
  comfyanonymous authored Aug 29, 2023
  
  bed116a1
- check for text attr and save · 18379dea
  Chris authored Aug 29, 2023
  
  18379dea
- copy metadata into modified image · edcff9ab
  Chris authored Aug 29, 2023
  
  edcff9ab
- refactor(ui): Switch statement, and handle other modes in group actions · 6944288a
  Michael Poutre authored Aug 29, 2023
  
  6944288a
- feat(ui): Add node mode toggles to group context menu · e30d546e
  Michael Poutre authored Aug 28, 2023
  
  e30d546e
- Use the same units for tile size in VAEDecodeTiled and VAEEncodeTiled. · 8ddd081b
  comfyanonymous authored Aug 29, 2023
  
  8ddd081b
- Merge branch 'master' of https://github.com/bvhari/ComfyUI · fbf375f1
  comfyanonymous authored Aug 29, 2023
  
  fbf375f1
28 Aug, 2023 12 commits
- No need to check filename extensions to detect shuffle controlnet. · 65cae62c
  comfyanonymous authored Aug 28, 2023
  
  65cae62c
- Put clip vision outputs on the CPU. · 4e89b2c2
  comfyanonymous authored Aug 28, 2023
  
  4e89b2c2
- Load clipvision model to GPU for faster performance. · a094b45c
  comfyanonymous authored Aug 28, 2023
  
  a094b45c
- Text encoder should initially load on the offload_device not the regular. · 1300a1bb
  comfyanonymous authored Aug 28, 2023
  
  1300a1bb
- Move ModelPatcher to model_patcher.py · f92074b8
  comfyanonymous authored Aug 28, 2023
  
  f92074b8
- Reduce min tile size for encode · d86b222f
  BVH authored Aug 28, 2023
  
  d86b222f
- Implement loras with norm keys. · 4798cf5a
  comfyanonymous authored Aug 28, 2023
  
  4798cf5a
- Make tile size in Tiled VAE encode/decode user configurable · 91965880
  BVH authored Aug 28, 2023
  
  91965880
- support on prompt event handler (#765) · 0faee118
  Dr.Lt.Data authored Aug 28, 2023
```
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
```
  0faee118
- Enable bf16-vae by default on ampere and up. · b8c7c770
  comfyanonymous authored Aug 27, 2023
  
  b8c7c770
- Fallback to slice attention if xformers doesn't support the operation. · 1c794a21
  comfyanonymous authored Aug 27, 2023
  
  1c794a21
- Make --bf16-vae work on torch 2.0 · d935ba50
  comfyanonymous authored Aug 27, 2023
  
  d935ba50
27 Aug, 2023 2 commits
- Merge branch 'increase_client_max_size' of https://github.com/ramyma/ComfyUI · 412596d3
  comfyanonymous authored Aug 27, 2023
  
  412596d3
- fix: cannot disable dynamicPrompts (#1327) · d9f49229
  Dr.Lt.Data authored Aug 28, 2023
```
* fix: cannot disable dynamicPrompts

* indent fix

---------
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
```
  d9f49229
26 Aug, 2023 2 commits
- Increase client_max_size to allow bigger request bodies · 0b6cf7a5
  ramyma authored Aug 26, 2023
  
  0b6cf7a5
- Fix lowvram model merging. · a57b0c79
  comfyanonymous authored Aug 26, 2023
  
  a57b0c79
25 Aug, 2023 4 commits
- The new smart memory management makes this unnecessary. · f72780a7
  comfyanonymous authored Aug 25, 2023
  
  f72780a7
- Move controlnet code to comfy/controlnet.py · c77f02e1
  comfyanonymous authored Aug 25, 2023
  
  c77f02e1
- Move lora code to comfy/lora.py · 15a7716f
  comfyanonymous authored Aug 25, 2023
  
  15a7716f
- Move text_projection to base clip model. · ec96f6d0
  comfyanonymous authored Aug 24, 2023
  
  ec96f6d0
24 Aug, 2023 6 commits
- Code cleanups. · 30eb92c3
  comfyanonymous authored Aug 24, 2023
  
  30eb92c3
- Try to free enough vram for control lora inference. · 51dde87e
  comfyanonymous authored Aug 24, 2023
  
  51dde87e
- Fix potential issue with text projection matrix multiplication. · e3d0a9a4
  comfyanonymous authored Aug 24, 2023
  
  e3d0a9a4
- Always shift text encoder to GPU when the device supports fp16. · cc44ade7
  comfyanonymous authored Aug 23, 2023
  
  cc44ade7
- Even with forced fp16 the cpu device should never use it. · a6ef08a4
  comfyanonymous authored Aug 23, 2023
  
  a6ef08a4
- Initialize text encoder to target dtype. · 00c0b2c5
  comfyanonymous authored Aug 23, 2023
  
  00c0b2c5
23 Aug, 2023 1 commit
- Save memory by storing text encoder weights in fp16 in most situations. · f081017c
  comfyanonymous authored Aug 23, 2023
```
Do inference in fp32 to make sure quality stays the exact same.
```
  f081017c