fix: combine FLUX CLIP entries into single repo entry
Both CLIP-L and T5-XXL come from the same repo, so they should be in one entry with multiple files, not two separate entries. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -263,28 +263,17 @@ model_categories:
|
||||
dest: "siglip-so400m-patch14-384.safetensors"
|
||||
|
||||
- repo_id: stabilityai/stable-diffusion-3.5-large
|
||||
description: CLIP-L - For FLUX text encoding
|
||||
size_gb: 1
|
||||
essential: true
|
||||
category: support
|
||||
type: clip
|
||||
format: fp32
|
||||
vram_gb: 1
|
||||
notes: CLIP-L text encoder required for FLUX models
|
||||
files:
|
||||
- source: "text_encoders/clip_l.safetensors"
|
||||
dest: "clip_l.safetensors"
|
||||
|
||||
- repo_id: stabilityai/stable-diffusion-3.5-large
|
||||
description: T5-XXL FP16 - For FLUX text encoding
|
||||
size_gb: 9
|
||||
description: CLIP-L and T5-XXL - For FLUX text encoding
|
||||
size_gb: 10
|
||||
essential: true
|
||||
category: support
|
||||
type: clip
|
||||
format: fp16
|
||||
vram_gb: 4
|
||||
notes: T5-XXL text encoder required for FLUX models
|
||||
notes: CLIP text encoders required for FLUX models
|
||||
files:
|
||||
- source: "text_encoders/clip_l.safetensors"
|
||||
dest: "clip_l.safetensors"
|
||||
- source: "text_encoders/t5xxl_fp16.safetensors"
|
||||
dest: "t5xxl_fp16.safetensors"
|
||||
|
||||
|
||||
Reference in New Issue
Block a user