|
13 | 13 | Run `pip install -r requirements.txt` to install python dependencies. You might experience version conflict on diffusers if you have other extensions that depend on other versions of diffusers. In this case, it is recommended to set up separate Python venvs. |
14 | 14 |
|
15 | 15 | ## Workflows |
16 | | -### [Generate foreground](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_fg_example_rgba.json) |
| 16 | +### [Generate foreground](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_fg_example_rgba.json) |
17 | 17 |  |
18 | 18 |
|
19 | | -### [Generate foreground (RGB + alpha)](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_fg_example.json) |
| 19 | +### [Generate foreground (RGB + alpha)](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_fg_example.json) |
20 | 20 | If you want more control of getting RGB images and alpha channel mask separately, you can use this workflow. |
21 | 21 |  |
22 | 22 |
|
23 | | -### [Blending (FG/BG)](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_cond_example.json) |
| 23 | +### [Blending (FG/BG)](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_cond_example.json) |
24 | 24 | Blending given FG |
25 | 25 |  |
26 | 26 |
|
27 | 27 | Blending given BG |
28 | 28 |  |
29 | 29 |
|
30 | | -### [Extract FG from Blended + BG](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_diff_fg.json) |
| 30 | +### [Extract FG from Blended + BG](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_diff_fg.json) |
31 | 31 |  |
32 | 32 |
|
33 | | -### [Extract BG from Blended + FG](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_diff_bg.json) |
| 33 | +### [Extract BG from Blended + FG](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_diff_bg.json) |
34 | 34 | [Forge impl's sanity check](https://github.com/layerdiffuse/sd-forge-layerdiffuse#sanity-check) sets `Stop at` to 0.5 to get better quality BG. |
35 | 35 | This workflow might be inferior compared to other object removal workflows. |
36 | 36 |  |
37 | 37 |
|
38 | | -### [Extract BG from Blended + FG (Stop at 0.5)](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_diff_bg_stop_at.json) |
| 38 | +### [Extract BG from Blended + FG (Stop at 0.5)](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_diff_bg_stop_at.json) |
39 | 39 | In [SD Forge impl](https://github.com/layerdiffuse/sd-forge-layerdiffuse), there is a `stop at` param that determines when |
40 | 40 | layer diffuse should stop in the denoising process. In the background, what this param does is unapply the LoRA and c_concat cond after a certain step |
41 | 41 | threshold. This is hard/risky to implement directly in ComfyUI as it requires manually loading a model that has every change except the layer diffusion |
42 | 42 | change applied. A workaround in ComfyUI is to have another img2img pass on the layer diffuse result to simulate the effect of `stop at` param. |
43 | 43 |  |
44 | 44 |
|
45 | 45 |
|
46 | | -### [Generate FG from BG combined](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_cond_fg_all.json) |
| 46 | +### [Generate FG from BG combined](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_cond_fg_all.json) |
47 | 47 | Combines previous workflows to generate blended and FG given BG. We found that there are some color variations in the extracted FG. Need to confirm |
48 | 48 | with layer diffusion authors whether this is expected. |
49 | 49 |  |
50 | 50 |
|
51 | | -### [2024-3-9] [Generate FG + Blended given BG](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_cond_joint_bg.json) |
| 51 | +### [2024-3-9] [Generate FG + Blended given BG](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_cond_joint_bg.json) |
52 | 52 | Need batch size = 2N. Currently only for SD15. |
53 | 53 |  |
54 | 54 |
|
55 | | -### [2024-3-9] [Generate BG + Blended given FG](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_cond_joint_fg.json) |
| 55 | +### [2024-3-9] [Generate BG + Blended given FG](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_cond_joint_fg.json) |
56 | 56 | Need batch size = 2N. Currently only for SD15. |
57 | 57 |  |
58 | 58 |
|
59 | | -### [2024-3-9] [Generate BG + FG + Blended together](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/examples/layer_diffusion_joint.json) |
| 59 | +### [2024-3-9] [Generate BG + FG + Blended together](https://github.com/huchenlei/ComfyUI-layerdiffuse/blob/main/example_workflows/layer_diffusion_joint.json) |
60 | 60 | Need batch size = 3N. Currently only for SD15. |
61 | 61 |  |
62 | 62 |
|
|
0 commit comments