Duplicate from InstantX/FLUX.1-dev-Controlnet-Canny

Co-authored-by: wangqixun <wangqixun@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+images/image_demo_weight.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+license: other
+license_name: flux-1-dev-non-commercial-license
+license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
+tags:
+- Text-to-Image
+- ControlNet
+- Diffusers
+- Stable Diffusion
+base_model: black-forest-labs/FLUX.1-dev
+---
+
+# FLUX.1-dev Controlnet
+
+We have completed the training of the first version. 
+The training was conducted with a total pixel count of `1024*1024` at multi-scale. 
+We trained for 30k steps using a batch size of 8*8.
+
+
+
+<img src="./images/image_demo.jpg" width = "800" />
+<img src="./images/image_demo_weight.png" width = "800" />
+
+
+# Diffusers version
+
+Please ensure that you have installed the latest version of [Diffusers](https://github.com/huggingface/diffusers).
+
+
+
+
+
+# Demo
+```python
+import torch
+from diffusers.utils import load_image
+from diffusers.pipelines.flux.pipeline_flux_controlnet import FluxControlNetPipeline
+from diffusers.models.controlnet_flux import FluxControlNetModel
+
+base_model = 'black-forest-labs/FLUX.1-dev'
+controlnet_model = 'InstantX/FLUX.1-dev-Controlnet-Canny'
+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")
+
+control_image = load_image("https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Canny/resolve/main/canny.jpg")
+prompt = "A girl in city, 25 years old, cool, futuristic"
+image = pipe(
+    prompt, 
+    control_image=control_image,
+    controlnet_conditioning_scale=0.6,
+    num_inference_steps=28, 
+    guidance_scale=3.5,
+).images[0]
+image.save("image.jpg")
+```
+
+
+
+
+
+
+

config.json

@@ -0,0 +1,19 @@
+{
+  "_class_name": "FluxControlNetModel",
+  "_diffusers_version": "0.30.0.dev0",
+  "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": 5,
+  "num_mode": null,
+  "num_single_layers": 0,
+  "patch_size": 1,
+  "pooled_projection_dim": 768
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b8b2c5f8aeca6d833e70af24585b44e26a6cd25d3076471272b61dbbef6e83
+size 3583232168