2502 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Robin Huang	5cf97f2a58	Restrict downloading to safetensor files only.	2024-08-13 12:29:35 -07:00
Robin Huang	bc85c0dc38	Add comment to not reply on internal.	2024-08-09 12:57:52 -07:00
Robin Huang	cf774c60b6	Validate model filename as well.	2024-08-08 16:18:36 -07:00
Robin Huang	b4647174a6	Add newline EOF.	2024-08-08 13:30:25 -07:00
Robin Huang	2ff2d6e1d3	Add new line.	2024-08-08 13:29:41 -07:00
Robin Huang	2e351ce2be	Revert "Use pydantic." ... This reverts commit 7461e8eb0073add315c65c6f5e361f0891bffc7d.	2024-08-08 13:27:12 -07:00
Robin Huang	836db8cf7f	Update comment.	2024-08-08 13:11:26 -07:00
Robin Huang	7461e8eb00	Use pydantic.	2024-08-08 13:06:26 -07:00
Robin Huang	db1ce51fdf	Use tuple type from annotations.	2024-08-08 12:53:17 -07:00
Robin Huang	5537d25e72	Add progress_interval as an optional parameter.	2024-08-07 17:04:26 -07:00
Robin Huang	c1d78d6890	Consolidate DownloadStatus and DownloadModelResult	2024-08-07 16:44:56 -07:00
Robin Huang	a6d8a93fa1	Remove DS_Store.	2024-08-07 12:58:31 -07:00
Robin Huang	b02ec058ff	Add download_model test checking for invalid paths.	2024-08-07 12:47:56 -07:00
Robin Huang	59933489bf	Validate that model subdirectory cannot contain relative paths.	2024-08-07 12:45:07 -07:00
Robin Huang	9632dded9e	Move server set up to right before run call.	2024-08-07 12:20:02 -07:00
Robin Huang	c36a559564	Use async mock.	2024-08-07 12:17:29 -07:00
Robin Huang	3881f03545	Fixed.	2024-08-07 12:12:01 -07:00
Robin Huang	c2cd09540d	Fixed	2024-08-07 12:11:32 -07:00
Robin Huang	2380ccce0a	Send "download_progress" as websocket event.	2024-08-06 21:22:01 -07:00
Robin Huang	cce1ccf9c9	Break up large function.	2024-08-06 21:21:51 -07:00
Robin Huang	8af203ecc6	Move client session init to async function.	2024-08-06 20:38:39 -07:00
Robin Huang	6976ccc5ca	Add model downloading endpoint.	2024-08-06 18:07:32 -07:00
comfyanonymous	b334605a66	Fix OOMs happening in some cases. ... A cloned model patcher sometimes reported a model was loaded on a device when it wasn't. v0.0.4	2024-08-06 13:36:04 -04:00
comfyanonymous	de17a9755e	Unload all models if there's an OOM error.	2024-08-06 03:30:28 -04:00
comfyanonymous	c14ac98fed	Unload models and load them back in lowvram mode no free vram.	2024-08-06 03:22:39 -04:00
Robin Huang	2894511893	Clone taesd with depth of 1 to reduce download size. (#4232)	2024-08-06 01:46:09 -04:00
Silver	f3bc40223a	Add format metadata to CLIP save to make compatible with diffusers safetensors loading (#4233)	2024-08-06 01:45:24 -04:00
Chenlei Hu	841e74ac40	Change browser test CI python to 3.8 (#4234)	2024-08-06 01:27:28 -04:00
comfyanonymous	2d75df45e6	Flux tweak memory usage.	2024-08-05 21:58:28 -04:00
Robin Huang	1abc9c8703	Stable release uses cached dependencies (#4231) ... * Release stable based on existing tag. * Update default cuda to 12.1.	2024-08-05 20:07:16 -04:00
comfyanonymous	8edbcf5209	Improve performance on some lowend GPUs.	2024-08-05 16:24:04 -04:00
comfyanonymous	e545a636ba	This probably doesn't work anymore.	2024-08-05 12:31:42 -04:00
bymyself	33e5203a2a	Don't cache index.html (#4211)	2024-08-05 12:25:28 -04:00
a-One-Fan	a178e25912	Fix Flux FP64 math on XPU (#4210)	2024-08-05 01:26:20 -04:00
comfyanonymous	78e133d041	Support simple diffusers Flux loras.	2024-08-04 22:05:48 -04:00
Silver	7afa985fba	Correct spelling 'token_weight_pars_t5' to 'token_weight_pairs_t5' (#4200)	2024-08-04 17:10:02 -04:00
comfyanonymous	ddb6a9f47c	Set the step in EmptySD3LatentImage to 16. ... These models work better when the res is a multiple of 16.	2024-08-04 15:59:02 -04:00
comfyanonymous	3b71f84b50	ONNX tracing fixes.	2024-08-04 15:45:43 -04:00
comfyanonymous	0a6b008117	Fix issue with some custom nodes.	2024-08-04 10:03:33 -04:00
comfyanonymous	56f3c660bf	ModelSamplingFlux now takes a resolution and adjusts the shift with it. ... If you want to sample Flux dev exactly how the reference code does use the same resolution as your image in this node.	2024-08-04 04:06:00 -04:00
comfyanonymous	f7a5107784	Fix crash.	2024-08-03 16:55:38 -04:00
comfyanonymous	91be9c2867	Tweak lowvram memory formula.	2024-08-03 16:44:50 -04:00
comfyanonymous	03c5018c98	Lower lowvram memory to 1/3 of free memory.	2024-08-03 15:14:07 -04:00
comfyanonymous	2ba5cc8b86	Fix some issues.	2024-08-03 15:06:40 -04:00
comfyanonymous	1e68002b87	Cap lowvram to half of free memory.	2024-08-03 14:50:20 -04:00
comfyanonymous	ba9095e5bd	Automatically use fp8 for diffusion model weights if: ... Checkpoint contains weights in fp8. There isn't enough memory to load the diffusion model in GPU vram.	2024-08-03 13:45:19 -04:00
comfyanonymous	f123328b82	Load T5 in fp8 if it's in fp8 in the Flux checkpoint.	2024-08-03 12:39:33 -04:00
comfyanonymous	63a7e8edba	More aggressive batch splitting.	2024-08-03 11:53:30 -04:00
comfyanonymous	0eea47d580	Add ModelSamplingFlux to experiment with the shift value. ... Default shift on Flux Schnell is 0.0	2024-08-03 03:54:38 -04:00
comfyanonymous	7cd0cdfce6	Add advanced model merge node for Flux model.	2024-08-02 23:20:53 -04:00