zer0int / CLIP-fine-tune-registers-gatedLinks
Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!
☆48Updated 6 months ago
Alternatives and similar repositories for CLIP-fine-tune-registers-gated
Users that are interested in CLIP-fine-tune-registers-gated are comparing it to the libraries listed below
Sorting:
- MoD Control Tile Upscaler for SDXL Pipeline☆61Updated 9 months ago
- Set of Utilities I Have Coded to Help Me Train RPGv6 on Flux1☆83Updated last year
- Gradio UI for training video models using finetrainers☆33Updated 7 months ago
- ☆43Updated last year
- NNT Neural Network Toolkit Custom Nodes for ComfyUI☆67Updated 11 months ago
- A ComfyUI custom node that loads and applies B-LoRA models.☆76Updated last year
- Adaptive ODE Solvers for ComfyUI☆53Updated last year
- Scripts for use with LongCLIP, including fine-tuning Long-CLIP☆63Updated 9 months ago
- A repository of ComfyUI nodes which modify the latent during the diffusion process.☆85Updated last year
- ☆43Updated 11 months ago
- ComfyUI powertools for SD1.5 and SDXL model merging☆94Updated 8 months ago
- ☆85Updated last year
- Implementing FlowEdit, maybe other inversion techniques for the Wan video generation model☆54Updated 9 months ago
- ☆73Updated 7 months ago
- ☆165Updated 2 weeks ago
- Custom LORA training on DynamiCrafter☆18Updated last year
- Janky implementation of DiffuseHigh for ComfyUI☆36Updated 7 months ago
- GUI for the new musubi-tuner☆51Updated 10 months ago
- Video2Video Framework for ComfyUI☆63Updated last year
- A custom node for ComfyUI that adds cinematic and movie scene styles to video generation prompts. This node helps create more dynamic and…☆46Updated 11 months ago
- Inference code of "Golden Noise for Diffusion Models: A Learning Framework".☆34Updated last year
- ☆92Updated last year
- ☆71Updated last year
- ☆53Updated 9 months ago
- This custom node for ComfyUI is designed to optimize latent generation for use with FLUX, Qwen, SDXL, SD3 and WAN modes. It provides flex…☆52Updated 3 months ago
- ComfyUI unofficial implementation of Thera - Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields☆35Updated 7 months ago
- ☆63Updated 7 months ago
- Allows to sample without generating any uncond with Stable Diffusion!☆51Updated last year
- A ComfyUI node implementation for ByteDance's Sa2VA☆89Updated last month
- A video clipper for Hunyuan video training.☆86Updated 4 months ago