kongo_junandClaude Fable 5
f25e3d6fa4
Krea2OstrisEditModelPatch object-patches diffusion_model.forward and drives block submodules directly (block.mod / block.attn / block.mlp), so the forward-wrapper swap never fires on the reference-latent paths. Every Krea2 block path begins with block.mod and ends with block.mlp, so this node triggers the swap with a forward_pre_hook on mod and a forward_hook on mlp. Verified on RTX 4090 / ComfyUI 0.26.2 with krea2_turbo_fp8 (no LoRA), blocks_to_swap=14: native, multi-reference and kv_cache paths all bit-exact vs no-swap, 6.4 GB resident instead of 12.9 GB. Runtime LoRA and bf16-scale checkpoints are documented as known-broken (CUDA invalid argument; shared bake-path suspect, see README). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TCjmaeny4KRS2TzXyYEgZS
15 lines
434 B
TOML
15 lines
434 B
TOML
[project]
|
|
name = "comfyui-jitblockswap"
|
|
description = "Block Swap (RAM Offload) node for native ComfyUI MODEL - run DiT models larger than VRAM by streaming transformer blocks from system RAM."
|
|
version = "0.2.0"
|
|
license = { file = "LICENSE" }
|
|
dependencies = []
|
|
|
|
[project.urls]
|
|
Repository = "https://github.com/lovemachine100/ComfyUI-JITBlockSwap"
|
|
|
|
[tool.comfy]
|
|
PublisherId = "kongo_jun"
|
|
DisplayName = "ComfyUI-JITBlockSwap"
|
|
Icon = ""
|