Qwen-LoRa / README.md
morikomorizz's picture
Update README.md
4e35fa4 verified

This is FireRed Image Edit, which combines Transformer Diffusion, Text Encoder, and VAE into a single file.

This model is still unstable for Text to Images (T2I) at resolutions of 1280x720 and above. However for image editing, the results are more stable and satisfactory.

Version 1

  • Combined With LoRa 8 Steps From FireRed Repo
  • MMProj stays in FP16
  • CFG 1.0 | Euler-A / Beta, Normal, Simple | 8 Steps