Update README.md

README.md

@@ -18,22 +18,26 @@ base_model: black-forest-labs/FLUX.1-dev
 <img src="./images/image_union.png" width = "1000" />
 
 
-## Diffusers version
-
-Until the next Diffusers pypi release, please install Diffusers from source and use [this PR(update 2024.08.20)](https://github.com/huggingface/diffusers/pull/9175) to be able to use. 
-TODO: change when new version.
+## Release
 
+- [2024/08/20] 🔥 Release the first beta version.
+Until the next Diffusers pypi release,
+please install Diffusers from source and use [this PR](https://github.com/huggingface/diffusers/pull/9175) to be able to use. 
 Before merging into the official main branch of diffusers, you can use this [diffusers_flux](https://github.com/instantX-research/diffusers_flux).
 
+- [2024/08/14] Release the alpha version.
+
+
+
 
 
 ## Checkpoint
 
 The training of union controlnet requires a significant amount of computational power. 
-The current release is only an alpha version checkpoint that has not been fully trained. 
-The beta version is in the training process. 
+The current release is the first beta version checkpoint that maybe not been fully trained. 
+The fully trainedbeta version is in the training process. 
 We have conducted ablation studies that have demonstrated the validity of the code. 
-The open-source release of the alpha version is solely to facilitate the rapid growth of the open-source community and the Flux ecosystem; 
+The open-source release of the first beta version is solely to facilitate the rapid growth of the open-source community and the Flux ecosystem; 
 it is common to encounter bad cases (please accept my apologies). 
 It is worth noting that we have found that even a fully trained Union model may not perform as well as specialized models, such as pose control. 
 However, as training progresses, the performance of the Union model will continue to approach that of specialized models.
@@ -63,7 +67,7 @@ from diffusers.models.controlnet_flux import FluxControlNetModel
 
 # load
 base_model = 'black-forest-labs/FLUX.1-dev'
-controlnet_model = 'InstantX/FLUX.1-dev-Controlnet-Union-alpha'
+controlnet_model = 'InstantX/FLUX.1-dev-Controlnet-Union'
 controlnet = FluxControlNetModel.from_pretrained(controlnet_model, torch_dtype=torch.bfloat16)
 pipe = FluxControlNetPipeline.from_pretrained(base_model, controlnet=controlnet, torch_dtype=torch.bfloat16)
 pipe.to("cuda")