imaginAIry/imaginairy/weight_management/weight_info/stable-diffusion-1-5_lora_diffusers.patterns.json
Bryce f97f6a3b4b feature: use refiners library for generation
BREAKING CHANGE

  - stable diffusion 1.5 + inpainting working
  - self-attention guidance working. improves image generation quality
  - tile-mode working
  - inpainting self-attention guidance working

disable/broken features:
  - sd 1.4, 2.0, 2.1
  - most of the samplers
  - pix2pix edit
  - most of the controlnets
  - memory management
  - python 3.8 support

wip
2023-11-22 13:22:00 -08:00

5 lines
432 B
JSON

[
"down_blocks.(0|1|2).attentions.(0|1).transformer_blocks.0.(attn1|attn2).processor.(to_k_lora|to_out_lora|to_q_lora|to_v_lora).(down|up).weight",
"mid_block.attentions.0.transformer_blocks.0.(attn1|attn2).processor.(to_k_lora|to_out_lora|to_q_lora|to_v_lora).(down|up).weight",
"up_blocks.(1|2|3).attentions.(0|1|2).transformer_blocks.0.(attn1|attn2).processor.(to_k_lora|to_out_lora|to_q_lora|to_v_lora).(down|up).weight"
]