comfyanonymous
|
36a7953142
|
Greatly improve lowvram sampling speed by getting rid of accelerate.
Let me know if this breaks anything.
|
11 months ago |
comfyanonymous
|
a5599ed42c
|
Add missing direct dep that gets pulled in by another.
|
1 year ago |
comfyanonymous
|
c910b4a01c
|
Remove unused code and torchdiffeq dependency.
|
1 year ago |
comfyanonymous
|
735ac4cf81
|
Remove pytorch_lightning dependency.
|
1 year ago |
comfyanonymous
|
cb180b9998
|
Add some missing direct dependencies that were getting pulled indirectly.
|
1 year ago |
comfyanonymous
|
f0a2b81cd0
|
Cleanup: Remove a bunch of useless files.
|
1 year ago |
藍+85CD
|
1ced2bdd2d
|
Specify safetensors version to avoid upstream errors
https://github.com/huggingface/safetensors/issues/142
|
2 years ago |
comfyanonymous
|
7a7c4e7f73
|
Not compatible with transformers below this version.
|
2 years ago |
comfyanonymous
|
54dbfaf2ec
|
Remove omegaconf dependency and some ci changes.
|
2 years ago |
pythongosssss
|
70b3311478
|
Removed socketio
|
2 years ago |
pythongosssss
|
a52aa9f4b5
|
Moved api out to server
Reworked sockets to use socketio
Added progress to nodes
Added highlight to active node
Added preview to saveimage node
|
2 years ago |
pythongosssss
|
639d21e5f7
|
Added aiohttp requirement
|
2 years ago |
comfyanonymous
|
534736b924
|
Add some low vram modes: --lowvram and --novram
|
2 years ago |
comfyanonymous
|
220afe3310
|
Initial commit.
|
2 years ago |