Commit ·
3341c5a
1
Parent(s): 92d685b
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,13 +6,12 @@ base_model:
|
|
| 6 |
This is FireRed Image Edit, which combines Transformer Diffusion, Text Encoder, and VAE into a single file.
|
| 7 |
For some reason FireRed 1.1 models (F16 or GGUF) have difficulty editing high resolution PNG images, JPG format is stable.
|
| 8 |
|
| 9 |
-
*Version 1*
|
| 10 |
- Combined With LoRa 8 Steps From FireRed Repo
|
| 11 |
- MMProj stays in FP16
|
| 12 |
-
- CFG
|
| 13 |
|
| 14 |
-
*Version 2*
|
| 15 |
- Combined With LoRa 4/8 Steps Qwen-Image-2512
|
| 16 |
-
- CFG 1.0 |
|
| 17 |
- Recommeded Sampler : Euler_a,
|
| 18 |
- 4 Steps for Fast, 8 Steps for better Quality
|
|
|
|
| 6 |
This is FireRed Image Edit, which combines Transformer Diffusion, Text Encoder, and VAE into a single file.
|
| 7 |
For some reason FireRed 1.1 models (F16 or GGUF) have difficulty editing high resolution PNG images, JPG format is stable.
|
| 8 |
|
| 9 |
+
*Version 1 : Image editing is good but bad at Text to Image Generation*
|
| 10 |
- Combined With LoRa 8 Steps From FireRed Repo
|
| 11 |
- MMProj stays in FP16
|
| 12 |
+
- CFG : 1
|
| 13 |
|
| 14 |
+
*Version 2 : Image Editing and Image Generation is more better than V1*
|
| 15 |
- Combined With LoRa 4/8 Steps Qwen-Image-2512
|
|
|
|
| 16 |
- Recommeded Sampler : Euler_a,
|
| 17 |
- 4 Steps for Fast, 8 Steps for better Quality
|