Implement SD15 Support

[huchenlei]

Closes #42.

LayerDiffuse SD15 brings 4 new models:

Generate FG

Use the apply node the same way as before.

Generate FG + Blended given BG

Need batch size = 2N.

Generate BG + Blended given FG

Need batch size = 2N.

Generate BG + FG + Blended together

Need batch size = 3N.

Notes:

• Dropdown options in previous nodes are updated. You will need to re-select the config for your previous workflows
• Unlike forge impl, which does cond concat for fg/bg/blended, in ComfyUI impl, the cond passed to layer diffusion node directly overwrites the global cond.
• LayerDiffuseDecode (Split) is added to decode RGBA every N images. It serves the purpose to only decode FG images in a batch.

[DrakenZA]

Very nice. Is the upgrade on diffusers a requirement ? (i disabled your check on my local copy, cause often changing diffusers can kill other custom nodes that havnt prepared their code for the newer diffusers etc)

edit: It does seem like it needs that version of diffusers. Hmm, hopefully other nodes i use are up to date haha :).

Thanks again for your work

[kacecarol]

can't wait to try, and got this:

Error occurred when executing KSampler:

CUDA error: invalid configuration argument
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

exactly the same workflow as yours.