Update README.md
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ tags:
|
|
18 |
This repository provides a collection of ControlNet checkpoints for
|
19 |
[FLUX.1-dev model](https://huggingface.co/black-forest-labs/FLUX.1-dev) by Black Forest Labs
|
20 |
|
21 |
-
![Example Picture 1](
|
22 |
|
23 |
[See our github](https://github.com/XLabs-AI/x-flux-comfyui) for comfy ui workflows.
|
24 |
![Example Picture 1](https://github.com/XLabs-AI/x-flux-comfyui/blob/main/assets/image1.png?raw=true)
|
@@ -33,7 +33,7 @@ Our collection supports 3 models:
|
|
33 |
- Depth (Midas)
|
34 |
|
35 |
Each ControlNet is trained on 1024x1024 resolution and works for 1024x1024 resolution.
|
36 |
-
We release **
|
37 |
|
38 |
Please, see our [ComfyUI custom nodes installation guide](https://github.com/XLabs-AI/x-flux-comfyui)
|
39 |
|
@@ -48,111 +48,37 @@ Also, some generation results with input images are provided in "Files and versi
|
|
48 |
To try our models, you have 2 options:
|
49 |
1. Use main.py from our [official repo](https://github.com/XLabs-AI/x-flux)
|
50 |
2. Use our custom nodes for ComfyUI and test it with provided workflows (check out folder /workflows)
|
|
|
51 |
|
52 |
See examples how to launch our models:
|
53 |
|
54 |
-
## Canny ControlNet (version
|
55 |
|
56 |
1. Clone our [x-flux-comfyui](https://github.com/XLabs-AI/x-flux-comfyui) custom nodes
|
57 |
2. Launch ComfyUI
|
58 |
3. Try our canny_workflow.json
|
59 |
|
60 |
-
![Example Picture 1](
|
61 |
-
![Example Picture 1](
|
62 |
-
![Example Picture 1](./assets/canny_v2_res3.png?raw=true)
|
63 |
|
64 |
|
65 |
-
##
|
66 |
|
67 |
-
1. Clone
|
68 |
-
2. Launch
|
|
|
69 |
|
70 |
-
|
71 |
-
|
72 |
-
--prompt "a viking man with white hair looking, cinematic, MM full HD" \
|
73 |
-
--image input_image_canny.jpg \
|
74 |
-
--control_type canny \
|
75 |
-
--repo_id XLabs-AI/flux-controlnet-collections --name flux-canny-controlnet.safetensors --device cuda --use_controlnet \
|
76 |
-
--model_type flux-dev --width 768 --height 768 \
|
77 |
-
--timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5 --guidance 4
|
78 |
|
79 |
-
```
|
80 |
-
![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/canny_example_1.png?raw=true)
|
81 |
|
82 |
-
##
|
83 |
|
84 |
1. Clone our [x-flux-comfyui](https://github.com/XLabs-AI/x-flux-comfyui) custom nodes
|
85 |
2. Launch ComfyUI
|
86 |
-
3. Try our
|
87 |
-
|
88 |
-
![Example Picture 1](./assets/depth_v2_res1.png?raw=true)
|
89 |
-
![Example Picture 1](./assets/depth_v2_res2.png?raw=true)
|
90 |
-
|
91 |
-
## Depth ControlNet (version 1)
|
92 |
-
1. Clone [our repo](https://github.com/XLabs-AI/x-flux), install requirements
|
93 |
-
2. Launch main.py in command line with parameters
|
94 |
-
```bash
|
95 |
-
python3 main.py \
|
96 |
-
--prompt "Photo of the bold man with beard and laptop, full hd, cinematic photo" \
|
97 |
-
--image input_image_depth1.jpg \
|
98 |
-
--control_type depth \
|
99 |
-
--repo_id XLabs-AI/flux-controlnet-collections --name flux-depth-controlnet.safetensors --device cuda --use_controlnet \
|
100 |
-
--model_type flux-dev --width 1024 --height 1024 \
|
101 |
-
--timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5 --guidance 4
|
102 |
-
|
103 |
-
```
|
104 |
-
![Example Picture 2](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/depth_example_1.png?raw=true)
|
105 |
-
|
106 |
-
```bash
|
107 |
-
python3 main.py \
|
108 |
-
--prompt "photo of handsome fluffy black dog standing on a forest path, full hd, cinematic photo" \
|
109 |
-
--image input_image_depth2.jpg \
|
110 |
-
--control_type depth \
|
111 |
-
--repo_id XLabs-AI/flux-controlnet-collections --name flux-depth-controlnet.safetensors --device cuda --use_controlnet \
|
112 |
-
--model_type flux-dev --width 1024 --height 1024 \
|
113 |
-
--timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5 --guidance 4
|
114 |
-
|
115 |
-
```
|
116 |
-
![Example Picture 2](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/depth_example_2.png?raw=true)
|
117 |
-
|
118 |
-
```bash
|
119 |
-
python3 main.py \
|
120 |
-
--prompt "Photo of japanese village with houses and sakura, full hd, cinematic photo" \
|
121 |
-
--image input_image_depth3.webp \
|
122 |
-
--control_type depth \
|
123 |
-
--repo_id XLabs-AI/flux-controlnet-collections --name flux-depth-controlnet.safetensors --device cuda --use_controlnet \
|
124 |
-
--model_type flux-dev --width 1024 --height 1024 \
|
125 |
-
--timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5 --guidance 4
|
126 |
-
|
127 |
-
```
|
128 |
-
![Example Picture 2](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/depth_example_3.png?raw=true)
|
129 |
-
|
130 |
-
|
131 |
-
## HED ControlNet (version 1)
|
132 |
-
```bash
|
133 |
-
python3 main.py \
|
134 |
-
--prompt "2d art of a sitting african rich woman, full hd, cinematic photo" \
|
135 |
-
--image input_image_hed1.jpg \
|
136 |
-
--control_type hed \
|
137 |
-
--repo_id XLabs-AI/flux-controlnet-collections --name flux-hed-controlnet.safetensors --device cuda --use_controlnet \
|
138 |
-
--model_type flux-dev --width 768 --height 768 \
|
139 |
-
--timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5 --guidance 4
|
140 |
-
|
141 |
-
```
|
142 |
-
![Example Picture 2](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/hed_example_1.png?raw=true)
|
143 |
-
|
144 |
-
```bash
|
145 |
-
python3 main.py \
|
146 |
-
--prompt "anime ghibli style art of a running happy white dog, full hd" \
|
147 |
-
--image input_image_hed2.jpg \
|
148 |
-
--control_type hed \
|
149 |
-
--repo_id XLabs-AI/flux-controlnet-collections --name flux-hed-controlnet.safetensors --device cuda --use_controlnet \
|
150 |
-
--model_type flux-dev --width 768 --height 768 \
|
151 |
-
--timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5 --guidance 4
|
152 |
-
|
153 |
-
```
|
154 |
-
![Example Picture 2](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/hed_example_2.png?raw=true)
|
155 |
|
|
|
156 |
|
157 |
## License
|
158 |
|
|
|
18 |
This repository provides a collection of ControlNet checkpoints for
|
19 |
[FLUX.1-dev model](https://huggingface.co/black-forest-labs/FLUX.1-dev) by Black Forest Labs
|
20 |
|
21 |
+
![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/depth_result1.png?raw=true)
|
22 |
|
23 |
[See our github](https://github.com/XLabs-AI/x-flux-comfyui) for comfy ui workflows.
|
24 |
![Example Picture 1](https://github.com/XLabs-AI/x-flux-comfyui/blob/main/assets/image1.png?raw=true)
|
|
|
33 |
- Depth (Midas)
|
34 |
|
35 |
Each ControlNet is trained on 1024x1024 resolution and works for 1024x1024 resolution.
|
36 |
+
We release **v3 versions** - better and realistic versions, which can be used directly in ComfyUI!
|
37 |
|
38 |
Please, see our [ComfyUI custom nodes installation guide](https://github.com/XLabs-AI/x-flux-comfyui)
|
39 |
|
|
|
48 |
To try our models, you have 2 options:
|
49 |
1. Use main.py from our [official repo](https://github.com/XLabs-AI/x-flux)
|
50 |
2. Use our custom nodes for ComfyUI and test it with provided workflows (check out folder /workflows)
|
51 |
+
3. Use gradio demo
|
52 |
|
53 |
See examples how to launch our models:
|
54 |
|
55 |
+
## Canny ControlNet (version 3)
|
56 |
|
57 |
1. Clone our [x-flux-comfyui](https://github.com/XLabs-AI/x-flux-comfyui) custom nodes
|
58 |
2. Launch ComfyUI
|
59 |
3. Try our canny_workflow.json
|
60 |
|
61 |
+
![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/canny_result1.png?raw=true)
|
62 |
+
![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/canny_result2.png?raw=true)
|
|
|
63 |
|
64 |
|
65 |
+
## Depth ControlNet (version 3)
|
66 |
|
67 |
+
1. Clone our [x-flux-comfyui](https://github.com/XLabs-AI/x-flux-comfyui) custom nodes
|
68 |
+
2. Launch ComfyUI
|
69 |
+
3. Try our depth_workflow.json
|
70 |
|
71 |
+
![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/depth_result1.png?raw=true)
|
72 |
+
![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/depth_result2.png?raw=true)
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
|
|
|
|
|
74 |
|
75 |
+
## HED ControlNet (version 3)
|
76 |
|
77 |
1. Clone our [x-flux-comfyui](https://github.com/XLabs-AI/x-flux-comfyui) custom nodes
|
78 |
2. Launch ComfyUI
|
79 |
+
3. Try our hed_workflow.json
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
+
![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/hed_result1.png?raw=true)
|
82 |
|
83 |
## License
|
84 |
|