Upload fixed Flux-Dev2Pro model

README.md

@@ -0,0 +1,20 @@
+---
+library_name: diffusers
+pipeline_tag: text-to-image
+---
+
+## Flux-Dev2Pro
+
+Flux-Dev2Pro finetunes the transformer of Flux-Dev to make LoRA training better.
+
+As discussed in this blog https://medium.com/@zhiwangshi28/why-flux-lora-so-hard-to-train-and-how-to-overcome-it-a0c70bc59eaf, LoRA trained on Flux-Dev often yields bad results, because without guidance distillation the LoRA training is diverged from the original training process. Flux-Dev2Pro recovers Flux-pro from Flux-dev by finetuning the model for many steps. Two epoch of 3M high quality images have been trained.
+
+The LoRA trained on Flux-Dev2pro yields a much better results when being applied on Flux-dev, just like LoRA trained on SDXL and being applied to SDXL-turbo/lightning.
+
+
+To use this model, run:
+```python
+from diffusers import FluxTransformer2DModel
+
+transformer = FluxTransformer2DModel.from_pretrained("ashen0209/Flux-Dev2Pro", torch_dtype=torch.bfloat16)
+```

transformer/config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "FluxTransformer2DModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "./flux-tuned-13k/transformer",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    16,
+    56,
+    56
+  ],
+  "guidance_embeds": true,
+  "in_channels": 64,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 19,
+  "num_single_layers": 38,
+  "patch_size": 1,
+  "pooled_projection_dim": 768
+}

transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e521b3e3cf1a5656c463fd9e2c434a159813da862377519deb34c85e2c78a568
+size 9983040304

transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64549d6b9c032179245b673fc39e28770b79710db074396c7c3cd2030f8138eb
+size 9949328904

transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144c8189ea40d514759100f4755dd689a58fb3f30a9ec05d7672054f299aee21
+size 3870584832