Mikubill / sd-paint-with-words
Implementation of 'Paint With Words' method in eDiff-I
☆25Updated last year
Alternatives and similar repositories for sd-paint-with-words:
Users that are interested in sd-paint-with-words are comparing it to the libraries listed below
- A SDXL compatible T2I-adapter implementation using Diffusers including a training script☆25Updated last year
- Public code release for the paper "ProCreate, Don’t Reproduce! Propulsive Energy Diffusion for Creative Generation"☆37Updated 2 months ago
- Sketch-to-Image Generation without retraining diffusion models☆49Updated last year
- A example pipeline to use InstructPix2Pix and the associated fine-tuned motion module☆31Updated last year
- Mask2Background for Stable Diffusion Web UI☆46Updated last year
- Proof of concept for control landmarks in diffusion models!☆85Updated last year
- implementation of AnimateDiff.☆32Updated last year
- Training InstructPi2Pix with SDXL.☆18Updated last year
- finetune your florence2 model easy☆20Updated 5 months ago
- BLIP2 captioning tool as an extension of AUTOMATIC's WebUI☆60Updated last year
- ☆28Updated 5 months ago
- [ECCV 2024] DC-Solver: Improving Predictor-Corrector Diffusion Sampler via Dynamic Compensation☆45Updated 4 months ago
- ControlAnimate Library☆48Updated last year
- Paper: "From Text to Pose to Image: Improving Diffusion Model Control and Quality"☆43Updated last month
- ☆27Updated 8 months ago
- A retrain of AnimateDiff to be conditional on an init image☆33Updated last year
- ☆35Updated 9 months ago
- Embedding Vector Visualization for Stable Diffusion web UI☆49Updated last year
- An efficient implementation of Stable-Diffusion-XL☆45Updated last year
- Let us control diffusion models!☆36Updated last year
- A simple tool to guess an HuggingFace repo URL from a state dict.☆38Updated 2 months ago
- PEA-Diffusion: Parameter-Efficient Adapter with Knowledge Distillation in non-English Text-to-Image Generation☆27Updated 2 months ago
- Apply unlimited masks to unlimited LoRA models☆47Updated last year
- SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution☆14Updated last year
- ☆32Updated 8 months ago
- sd3 dreambooth lora training book, adapted from the diffusers doc☆42Updated 7 months ago
- Unofficial implementation. Stable diffusion model trained by AI Feedback-Based Self-Training Direct Preference Optimization.☆59Updated 10 months ago