| --- |
| base_model: |
| - FireRedTeam/FireRed-Image-Edit-1.1 |
| --- |
| |
| This is FireRed Image Edit, which combines Transformer Diffusion, Text Encoder, and VAE into a single file. |
| For some reason FireRed 1.1 models (F16 or GGUF) have difficulty editing high resolution PNG images, JPG format is stable. |
|
|
| *Version 1 : Image editing is good but bad at Text to Image Generation* |
| - Combined With LoRa 8 Steps From FireRed Repo |
| - MMProj stays in FP16 |
| - CFG : 1 |
|
|
| *Version 2 : Image Editing and Image Generation is more better than V1* |
| - Combined With LoRa 4/8 Steps Qwen-Image-2512 |
| - Recommeded Sampler : Euler_a, |
| - 4 Steps for Fast, 8 Steps for better Quality |
