mirror of
https://github.com/mudler/LocalAI.git
synced 2026-01-06 02:29:54 -06:00
c2e4a1f29b
* feat(stablediffusion): Passthrough more parameters to support z-image and flux2 Signed-off-by: Richard Palethorpe <io@richiejp.com> * chore(z-image): Add Z-Image-Turbo GGML to library Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(stablediffusion-ggml): flush stderr and check errors when writing PNG Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(stablediffusion-ggml): Re-allocate Go strings in C++ Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(stablediffusion-ggml): Try to avoid segfaults Signed-off-by: Richard Palethorpe <io@richiejp.com> * fix(stablediffusion-ggml): Init sample and easycache params Signed-off-by: Richard Palethorpe <io@richiejp.com> --------- Signed-off-by: Richard Palethorpe <io@richiejp.com> Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
16 lines
311 B
YAML
16 lines
311 B
YAML
---
|
|
name: "Z-Image-GGML"
|
|
|
|
config_file: |
|
|
backend: stablediffusion-ggml
|
|
cfg_scale: 1
|
|
name: z-image-test
|
|
options:
|
|
- diffusion_model
|
|
- llm_path:Qwen3-4B.Q4_K_M.gguf
|
|
- vae_path:ae.safetensors
|
|
- offload_params_to_cpu:true
|
|
parameters:
|
|
model: z_image_turbo-Q4_K.gguf
|
|
step: 25
|