Birch-san / regional-attnLinks
☆19Updated last year
Alternatives and similar repositories for regional-attn
Users that are interested in regional-attn are comparing it to the libraries listed below
Sorting:
- A comprehensive codebase for training and finetuning Image <> Latent models.☆49Updated 10 months ago
- ☆33Updated last year
- MoD Control Tile Upscaler for SDXL Pipeline☆61Updated 10 months ago
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".☆34Updated last year
- ComfyUI implementation of the paper https://arxiv.org/pdf/2410.02416 "APG".☆34Updated last year
- Batched Runge-Kutta Samplers for ComfyUI☆64Updated last year
- Custom LORA training on DynamiCrafter☆18Updated last year
- ComfyUI nodes to use APG scaling for CFG☆29Updated last year
- ☆54Updated 2 years ago
- Greatly increase the diversity of your generated images in Automatic1111 WebUI through Condition-Annealed Sampling.☆109Updated last year
- ☆14Updated last year
- Gradio UI for training video models using finetrainers☆33Updated 8 months ago
- ☆29Updated last year
- Motion Module fine tuner for AnimateDiff.☆78Updated 2 years ago
- https://github.com/xie-lab-ml/Golden-Noise-for-Diffusion-Models for ComfyUI☆17Updated last year
- ComfyUI unofficial implementation of Thera - Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields☆35Updated last week
- ComfyUI node to apply the ResAdapter Unet patch for SD1.5 models☆31Updated 10 months ago
- Allows native usage of ModelScope based Text To Video Models in ComfyUI☆27Updated last year
- ComfyUI implementation of Motion-I2V☆41Updated last year
- Just code snipet☆32Updated last year
- ComfyUI powertools for SD1.5 and SDXL model merging☆94Updated 9 months ago
- Create Latents with Perlin Noise in any shape (dimensionality). Works with Flux, SD3 and other 16d latent models.☆34Updated last year
- Diffusers Implementation of Controlling Text-to-Image Diffusion by Orthogonal Finetuning☆35Updated 2 years ago
- ☆43Updated last year
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model☆54Updated 10 months ago
- Adaptive ODE Solvers for ComfyUI☆53Updated last year
- Wildly unsound and experimental sampling for ComfyUI☆28Updated 5 months ago
- Understand Human Behavior to Align True Needs☆25Updated last year
- Provides the ability to set the temperature for both UNET and CLIP. For ComfyUI. Has for side effect to improve non-native resolutions.☆44Updated last year
- Allows to sample without generating any uncond with Stable Diffusion!☆51Updated last year