imaginAIry/imaginairy/weight_management/weight_info/stable-diffusion-1-5_text_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

7 lines
371 B
JSON

[
"text_model.(embeddings|final_layer_norm)",
"text_model.embeddings.(position_embedding|token_embedding)",
"text_model.encoder.layers.(0|1|2|3|4|5|6|7|8|9|10|11).(layer_norm1|layer_norm2)",
"text_model.encoder.layers.(0|1|2|3|4|5|6|7|8|9|10|11).mlp.(fc1|fc2)",
"text_model.encoder.layers.(0|1|2|3|4|5|6|7|8|9|10|11).self_attn.(k_proj|out_proj|q_proj|v_proj)"
]