revert to 8-step Q5_0 GGUF (4-step OOMs during build conversion)

Dockerfile

@@ -39,20 +39,15 @@ RUN chmod +x /app/sd-cli
 
 RUN mkdir -p /app/models
 
-# Download Z-Anime distill 4-step BF16 (~12.3GB), convert to Q5_K_M GGUF, delete source
-RUN curl -fL --retry 3 --retry-delay 5 -o /app/models/z-anime-distill-4step-bf16.safetensors \
-    "https://huggingface.co/SeeSee21/Z-Anime/resolve/main/diffusion_models/z-anime-distill-4step-bf16.safetensors" \
-    && /app/sd-cli -M convert \
-        -m /app/models/z-anime-distill-4step-bf16.safetensors \
-        -o /app/models/z-anime-distill-4step-Q5_0.gguf \
-        --type q5_0 \
-    && rm /app/models/z-anime-distill-4step-bf16.safetensors
-
-# Download Qwen3-4B text encoder Q8_0 GGUF (~4.28GB)
+# Z-Anime distill 8-step Q5_0 GGUF (~4.51GB)
+RUN curl -fL --retry 3 --retry-delay 5 -o /app/models/z-anime-8steps-q5_0.gguf \
+    "https://huggingface.co/DaNS2025/Z-Anime_8-steps.GGUF/resolve/main/Z-Anime-8steps.q5_0.gguf"
+
+# Qwen3-4B text encoder Q8_0 GGUF (~4.28GB)
 RUN curl -fL --retry 3 --retry-delay 5 -o /app/models/qwen3_4b_q8_0.gguf \
     "https://huggingface.co/worstplayer/Z-Image_Qwen_3_4b_text_encoder_GGUF/resolve/main/Qwen_3_4b-Q8_0.gguf"
 
-# Download VAE (~168MB)
+# VAE (~168MB)
 RUN curl -fL --retry 3 --retry-delay 5 -o /app/models/ae.safetensors \
     "https://huggingface.co/SeeSee21/Z-Anime/resolve/main/vae/ae.safetensors"
 

app.py

@@ -7,12 +7,12 @@ import gradio as gr
 # ---------------------------------------------------------------------------
 # Model paths (downloaded at build time)
 # ---------------------------------------------------------------------------
-DIFFUSION = "/app/models/z-anime-distill-4step-Q5_0.gguf"
+DIFFUSION = "/app/models/z-anime-8steps-q5_0.gguf"
 LLM = "/app/models/qwen3_4b_q8_0.gguf"
 VAE = "/app/models/ae.safetensors"
 
 RESOLUTIONS = ["512x512", "768x512", "512x768"]
-STEPS = 4
+STEPS = 8
 CFG = 1.0
 TIMEOUT = 10800
 
@@ -122,7 +122,7 @@ with gr.Blocks(title="Z-Anime (CPU)") as demo:
                 res_input = gr.Dropdown(choices=RESOLUTIONS, value="512x512",
                     label="Resolution")
                 seed_input = gr.Number(value=-1, label="Seed (-1=random)", precision=0)
-            gen_btn = gr.Button("Generate (4 steps, CFG 1)", variant="primary", size="lg")
+            gen_btn = gr.Button("Generate (8 steps, CFG 1)", variant="primary", size="lg")
         with gr.Column():
             output_img = gr.Image(type="pil", label="Output")
             status_box = gr.Textbox(label="Status", interactive=False)