The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
comfyanonymous 9ac0b487ac Make --gpu-only put intermediate values in GPU memory instead of cpu. 12 months ago
..
chainner_models Support DiffBIR SwinIR models. 1 year ago
nodes_canny.py Make --gpu-only put intermediate values in GPU memory instead of cpu. 12 months ago
nodes_clip_sdxl.py CLIPTextEncodeSDXL now works when prompts are of very different sizes. 1 year ago
nodes_compositing.py Fix SplitImageWithAlpha and JoinImageWithAlpha. 1 year ago
nodes_custom_sampler.py Add SDTurboScheduler node. 12 months ago
nodes_freelunch.py Implement updated FreeU as _for_testing->FreeU_V2 node 1 year ago
nodes_hypernetwork.py Support hypernetwork with mish activation function and layer norm. 1 year ago
nodes_hypertile.py Fix hypertile. 12 months ago
nodes_images.py Fix output APNG not working with ffmpeg. 12 months ago
nodes_latent.py Add LatentInterpolate to interpolate between latents. 1 year ago
nodes_mask.py Fix MaskComposite 1 year ago
nodes_model_advanced.py .sigma and .timestep now return tensors on the same device as the input. 12 months ago
nodes_model_downscale.py Allow controlling downscale and upscale methods in PatchModelAddDownscale. 1 year ago
nodes_model_merging.py Add a CLIPSave node to save CLIP model weights. 1 year ago
nodes_post_processing.py Make --gpu-only put intermediate values in GPU memory instead of cpu. 12 months ago
nodes_rebatch.py Increase maximum batch size in LatentRebatch. 1 year ago
nodes_tomesd.py Add some more transformer hooks and move tomesd to comfy_extras. 1 year ago
nodes_upscale_model.py Support DiffBIR SwinIR models. 1 year ago
nodes_video_model.py Fix typo. 1 year ago