InvokeAI/invokeai/configs/flux/flux1-dev.yaml

repo_id: "black-forest-labs/FLUX.1-dev"
repo_ae: "ae.safetensors"
max_seq_len: 512
params:
  in_channels: 64
  vec_in_dim: 768
  context_in_dim: 4096
  hidden_size: 3072
  mlp_ratio: 4.0
  num_heads: 24
  depth: 19
  depth_single_blocks: 38
  axes_dim:
  - 16
  - 56
  - 56
  theta: 10_000
  qkv_bias: True
  guidance_embed: True
Add backend functions and classes for Flux implementation, Update the way flux encoders/tokenizers are loaded for prompt encoding, Update way flux vae is loaded 2024-08-16 21:04:48 +00:00			`repo_id: "black-forest-labs/FLUX.1-dev"`
			`repo_ae: "ae.safetensors"`
Select dev/schnell based on state dict, use correct max seq len based on dev/schnell, and shift in inference, separate vae flux params into separate config 2024-08-19 18:41:28 +00:00			`max_seq_len: 512`
Add backend functions and classes for Flux implementation, Update the way flux encoders/tokenizers are loaded for prompt encoding, Update way flux vae is loaded 2024-08-16 21:04:48 +00:00			`params:`
			`in_channels: 64`
			`vec_in_dim: 768`
			`context_in_dim: 4096`
			`hidden_size: 3072`
			`mlp_ratio: 4.0`
			`num_heads: 24`
			`depth: 19`
			`depth_single_blocks: 38`
			`axes_dim:`
			`- 16`
			`- 56`
			`- 56`
			`theta: 10_000`
			`qkv_bias: True`
			`guidance_embed: True`