mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-03-04 00:37:32 +08:00
d159142615
* refactor: rename Mahiro CFG to Similarity-Adaptive Guidance Rename the display name to better describe what the node does: adaptively blends guidance based on cosine similarity between positive and negative conditions. Amp-Thread-ID: https://ampcode.com/threads/T-019c0d36-8b43-745f-b7b2-e35b53f17fa1 Co-authored-by: Amp <amp@ampcode.com> * feat: add search aliases for old mahiro name Amp-Thread-ID: https://ampcode.com/threads/T-019c0d36-8b43-745f-b7b2-e35b53f17fa1 * rename: Similarity-Adaptive Guidance → Positive-Biased Guidance (per reviewer) - display_name changed to 'Positive-Biased Guidance' to avoid SAG acronym collision - search_aliases expanded: mahiro, mahiro cfg, similarity-adaptive guidance, positive-biased cfg - ruff format applied --------- Co-authored-by: Amp <amp@ampcode.com> Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
66 lines
2.0 KiB
Python
66 lines
2.0 KiB
Python
from typing_extensions import override
|
|
import torch
|
|
import torch.nn.functional as F
|
|
|
|
from comfy_api.latest import ComfyExtension, io
|
|
|
|
|
|
class Mahiro(io.ComfyNode):
|
|
@classmethod
|
|
def define_schema(cls):
|
|
return io.Schema(
|
|
node_id="Mahiro",
|
|
display_name="Positive-Biased Guidance",
|
|
category="_for_testing",
|
|
description="Modify the guidance to scale more on the 'direction' of the positive prompt rather than the difference between the negative prompt.",
|
|
inputs=[
|
|
io.Model.Input("model"),
|
|
],
|
|
outputs=[
|
|
io.Model.Output(display_name="patched_model"),
|
|
],
|
|
is_experimental=True,
|
|
search_aliases=[
|
|
"mahiro",
|
|
"mahiro cfg",
|
|
"similarity-adaptive guidance",
|
|
"positive-biased cfg",
|
|
],
|
|
)
|
|
|
|
@classmethod
|
|
def execute(cls, model) -> io.NodeOutput:
|
|
m = model.clone()
|
|
|
|
def mahiro_normd(args):
|
|
scale: float = args["cond_scale"]
|
|
cond_p: torch.Tensor = args["cond_denoised"]
|
|
uncond_p: torch.Tensor = args["uncond_denoised"]
|
|
# naive leap
|
|
leap = cond_p * scale
|
|
# sim with uncond leap
|
|
u_leap = uncond_p * scale
|
|
cfg = args["denoised"]
|
|
merge = (leap + cfg) / 2
|
|
normu = torch.sqrt(u_leap.abs()) * u_leap.sign()
|
|
normm = torch.sqrt(merge.abs()) * merge.sign()
|
|
sim = F.cosine_similarity(normu, normm).mean()
|
|
simsc = 2 * (sim + 1)
|
|
wm = (simsc * cfg + (4 - simsc) * leap) / 4
|
|
return wm
|
|
|
|
m.set_model_sampler_post_cfg_function(mahiro_normd)
|
|
return io.NodeOutput(m)
|
|
|
|
|
|
class MahiroExtension(ComfyExtension):
|
|
@override
|
|
async def get_node_list(self) -> list[type[io.ComfyNode]]:
|
|
return [
|
|
Mahiro,
|
|
]
|
|
|
|
|
|
async def comfy_entrypoint() -> MahiroExtension:
|
|
return MahiroExtension()
|