qnloft
/
ComfyUI
mirror of https://github.com/comfyanonymous/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
ComfyUI/comfy
History
Svein Ove Aas 5f50263088
Replace use of .view with .reshape (#4522) 
When generating images with fp8_e4_m3 Flux and batch size >1, using --fast, ComfyUI throws a "view size is not compatible with input tensor's size and stride" error pointing at the first of these two calls to view.

As reshape is semantically equivalent to view except for working on a broader set of inputs, there should be no downside to changing this. The only difference is that it clones the underlying data in cases where .view would error out. I have confirmed that the output still looks as expected, but cannot confirm that no mutable use is made of the tensors anywhere.

Note that --fast is only marginally faster than the default.
 		2024-08-21 11:21:48 -04:00
..
cldm "auto" type is only relevant to the SetUnionControlNetType node. 2024-07-22 11:30:38 -04:00
extra_samplers Cleanup uni_pc inpainting. 2024-02-23 02:39:35 -05:00
k_diffusion Automatically use RF variant of dpmpp_2s_ancestral if RF model. 2024-08-18 00:47:25 -04:00
ldm Indentation. 2024-08-17 23:00:44 -04:00
sd1_tokenizer Initial commit. 2023-01-16 22:37:14 -05:00
t2i_adapter Controlnet refactor. 2024-06-27 18:43:11 -04:00
taesd Improvements to the TAESD3 implementation. 2024-06-16 02:04:24 -04:00
text_encoders Support loading long clipl model with the CLIP loader node. 2024-08-20 10:46:36 -04:00
checkpoint_pickle.py Remove pytorch_lightning dependency. 2023-06-13 10:11:33 -04:00
cli_args.py Add --fast argument to enable experimental optimizations. 2024-08-20 11:55:51 -04:00
clip_config_bigg.json Fix potential issue with non clip text embeddings. 2024-07-30 14:41:13 -04:00
clip_model.py Support loading long clipl model with the CLIP loader node. 2024-08-20 10:46:36 -04:00
clip_vision.py support clip-vit-large-patch14-336 (#4042) 2024-07-17 13:12:50 -04:00
clip_vision_config_g.json Add support for clip g vision model to CLIPVisionLoader. 2023-08-18 11:13:29 -04:00
clip_vision_config_h.json Add support for unCLIP SD2.x models. 2023-04-01 23:19:15 -04:00
clip_vision_config_vitl.json Add support for unCLIP SD2.x models. 2023-04-01 23:19:15 -04:00
clip_vision_config_vitl_336.json support clip-vit-large-patch14-336 (#4042) 2024-07-17 13:12:50 -04:00
conds.py Fix bug with cosxl edit model. 2024-06-10 16:00:03 -04:00
controlnet.py xlabs Flux controlnet implementation. (#4260) 2024-08-12 21:22:22 -04:00
diffusers_convert.py Fix saving text encoder in fp8. 2024-04-02 11:46:34 -04:00
diffusers_load.py load_unet -> load_diffusion_model with a model_options argument. 2024-08-12 23:20:57 -04:00
float.py Better subnormal fp8 stochastic rounding. Thanks Ashen. 2024-08-19 13:38:03 -04:00
gligen.py Fix gligen lowvram mode. 2024-02-18 02:20:23 -05:00
latent_formats.py Implement support for taef1 latent previews (#4409) 2024-08-16 12:53:13 -04:00
lora.py Simpletrainer lycoris format. 2024-08-20 12:05:13 -04:00
model_base.py Add --fast argument to enable experimental optimizations. 2024-08-20 11:55:51 -04:00
model_detection.py Fix issues with #4302 and support loading diffusers format flux. 2024-08-10 21:28:24 -04:00
model_management.py Remove useless line, adjust windows default reserved vram. 2024-08-21 00:47:19 -04:00
model_patcher.py Bug fixes. 2024-08-19 16:28:55 -04:00
model_sampling.py Basic Flux Schnell and Flux Dev model implementation. 2024-08-01 09:49:29 -04:00
ops.py Replace use of .view with .reshape (#4522) 2024-08-21 11:21:48 -04:00
options.py Only parse command line args when main.py is called. 2023-09-13 11:38:20 -04:00
sample.py Reshape the empty latent image to the right amount of channels if needed. 2024-06-08 02:35:08 -04:00
sampler_helpers.py Make ComfyUI split batches a higher priority than weight offload. 2024-08-01 16:39:59 -04:00
samplers.py Automatically use RF variant of dpmpp_2s_ancestral if RF model. 2024-08-18 00:47:25 -04:00
sd.py Support loading long clipl model with the CLIP loader node. 2024-08-20 10:46:36 -04:00
sd1_clip.py Properly set if clip text pooled projection instead of using hack. 2024-08-20 10:46:36 -04:00
sd1_clip_config.json Fix potential issue with non clip text embeddings. 2024-07-30 14:41:13 -04:00
sdxl_clip.py Properly set if clip text pooled projection instead of using hack. 2024-08-20 10:46:36 -04:00
supported_models.py Try to fix SDXL OOM issue on some configurations. 2024-08-14 23:08:54 -04:00
supported_models_base.py Add a way to set model dtype and ops from load_checkpoint_guess_config. 2024-08-11 08:50:34 -04:00
types.py Fix UnetParams annotation typo (#3589) 2024-05-27 19:30:35 -04:00
utils.py Fix issues with #4302 and support loading diffusers format flux. 2024-08-10 21:28:24 -04:00