Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-to-image
|
| 3 |
+
library_name: transformers
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
**FluxKontext-T5** is FluxKontext Dev fine-tuned on the 1.5 M GPT-Image-Edit Dataset using:
|
| 8 |
+
|
| 9 |
+
- **Original Text encoders:** T5 & CLIP text encoder
|
| 10 |
+
(checkpoint bundle still includes Qwen-VL weights from codebase UniWorld-V1, but inference uses only T5 + CLIP text encoder)
|