schema = "m64/capsule@1" description = "Qwen-Image-2.1 Uncensored Omni text-to-image on GB10 (diffusers). ChatR Labs' uncensored Omni adapter (step 90,000, merged into Qwen's 7B Qwen-Image-2.1 at strength 1.0, BF16) at 1024x1024, 35 steps, true CFG 5.0, the model card's settings. Can produce adult content. Qwen Research License: non-commercial use only. Runs fully offline." kinds = ["image.generate"] authors = ["dh7"] license = "other" [hardware] platform = "linux-aarch64" gpu = "NVIDIA GB10" gpu_count = 1 vram_gb = 56 driver = ">=580" disk_gb = 50 [runtime] sandbox = "container" # No image: the Dockerfile builds on nvcr.io/nvidia/pytorch:25.09-py3 + diffusers 0.41.0, pinned by digest. gpu = true shm_gb = 8 internal_port = 9049 health = "/health" expected_load_seconds = 1200 model_name = "qwen-image-2.1-uncensored-omni" user = "65534:65534" [[artifacts]] type = "hf" repo = "Qwen/Qwen-Image-2.1" revision = "790c92633540aa0cb11d9abf19eb46d861714758" include = [ ".gitattributes", "LICENSE", "README.md", "model_index.json", "processor/*", "scheduler/*", "text_encoder/*", "tokenizer/*", "transformer/*", "vae/*", ] mount = "/weights/qwen-image-2.1" [[artifacts]] type = "hf" repo = "chatrlabs/Qwen-Image-2.1-Uncensored-Omni-Quantized" revision = "36d4b08d490fd8827a0dc5e02ac6a066a37a12c7" include = [".gitattributes", "BENCHMARK.md", "LICENSE", "Notice", "README.md", "SHA256SUMS", "qwen-image-2.1-step90000-BF16/*"] mount = "/weights/omni" # The server's own defaults (qwen_image_21_omni_server.py), which every request gets: callers can only send # prompt and seed. Returned as params_used. [params] output_resolution = 1024 num_inference_steps = 35 true_cfg_scale = 5.0 negative_prompt = " " [routes] extra = ["/v1/config"]