wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-07-03 13:19:23 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

Update AGENTS.md

Browse Source
This commit is contained in:
comfyanonymous 2026-07-02 16:29:54 -07:00 committed by GitHub
parent 35c1470935
commit e7af482c00
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
AGENTS.md
View File

@ -181,6 +181,11 @@
tensors just to use tensor methods for scalar or structural calculations. tensors just to use tensor methods for scalar or structural calculations.
- Avoid unnecessary casts and transfers. Preserve the intended compute dtype, - Avoid unnecessary casts and transfers. Preserve the intended compute dtype,
storage dtype, bias dtype, and original tensor shape metadata. storage dtype, bias dtype, and original tensor shape metadata.
- Keep model-native latent layout handling inside the model or latent-format
owner, not in helper nodes. Do not collapse, expand, pack, or unpack latent
dimensions in nodes or other caller-side adapters just to satisfy a model
forward; the model path should consume and return the native latent shape for
that model family.
- Assume inputs to the main model forward are already in the compute dtype by - Assume inputs to the main model forward are already in the compute dtype by
default, except integer inputs such as some model timestep tensors. Do not add default, except integer inputs such as some model timestep tensors. Do not add
defensive or convenience casts in model code; it is better for invalid dtype defensive or convenience casts in model code; it is better for invalid dtype
@ -244,6 +249,10 @@
- Model implementations should add the minimal number of ComfyUI nodes required - Model implementations should add the minimal number of ComfyUI nodes required
to run the model. Reuse existing nodes as much as possible; adapting the model to run the model. Reuse existing nodes as much as possible; adapting the model
to work with existing nodes is strongly preferred over creating new nodes. to work with existing nodes is strongly preferred over creating new nodes.
- Nodes should output only values they own. Do not add pass-through outputs for
workflow convenience unless the node is explicitly an output node. Existing
models, latents, conditioning, or other inputs should flow directly to the
next consumer instead of being re-emitted unchanged.
- Node-level code must not patch model code directly. Any node behavior that - Node-level code must not patch model code directly. Any node behavior that
modifies, wraps, hooks, or changes model behavior must go through the model modifies, wraps, hooks, or changes model behavior must go through the model
patcher class instead of reaching into model internals. patcher class instead of reaching into model internals.