Upload README.md with huggingface_hub

10a824f verified 17 days ago

6.67 kB

license: unknown
pipeline_tag: text-to-image
tags:
  - text-to-image
  - anime
  - inpainting
  - controlnet
  - distilled
  - turbo

Anima Turbo — anime generation + LLLite inpainting

A 4B anime-native turbo model — ≈6 s per 1024² image on an RTX 5090 at 10 steps, with a ControlNet-LLLite inpainting patch for masked edits.

What this repo is: the Anima Turbo denoiser, the LLLite inpainting patch, a Qwen3-0.6B text encoder and the Qwen-Image VAE — weights only, not a retrain. The settings below are the values these weights are actually run with day to day.

Samples

Anime is what this model is for — these are 10-step, guidance 1.0 renders.


_{prompt: `masterpiece, best quality, anime illustration of a girl in a school uniform standing on a rooftop at sunset, detailed cel shading, clean linework, dramatic sky` — 1024×1024, 10 steps, guidance 1.0, seed 21}	_{prompt: `masterpiece, best quality, anime illustration, a silver-armored knight with a glowing blue sword in a ruined cathedral, dramatic lighting, detailed` — 1024×1024, 10 steps, guidance 1.0, seed 7}

_{prompt: `masterpiece, best quality, anime background art of a quiet japanese street in summer, blue sky, detailed clouds, vibrant colors, no people` — 1024×1024, 10 steps, guidance 1.0, seed 22}	_{prompt: `masterpiece, best quality, anime illustration, a young woman with long black hair in a white summer dress standing in a flower meadow, blue sky` — 1024×1024, 10 steps, guidance 1.0, seed 21}

Inpainting (`img2img` + mask)

img2img on this model is masked inpainting through the LLLite patch, not strength-based restyling. Supply the source image, a white-on-black mask of the region to change, and a full prompt describing the desired result.


_{source — the meadow render above, seed 21}	_{mask — ellipse over head and torso; white = repaint}	_{result — prompt changed to `…a young woman with vivid red hair…`, seed 43. Hair tone, eyes and bodice change; the meadow, pose, dress and framing are untouched.}

What inpainting does and does not do here

Recolouring and restyling inside the mask works well — hair colour, eye colour, garment detail. Everything outside the mask is preserved exactly.
Adding new objects is unreliable. wearing a wide straw sun hat on the same mask produced no hat, only a slight expression change. LLLite is a control patch conditioning an existing composition, not an instruction editor — write the whole scene as you want it, and expect changes in the masked region to stay close to the underlying shapes.
Without a mask, img2img is effectively a no-op — the control signal reproduces the input. Style-transfer prompts return the source image unchanged. If nothing is changing, check that a mask was actually sent.

Recommended settings

Values this build is run with in practice.

Parameter	Production value	Meaning
`width`	`1024`	Output width in pixels
`height`	`1024`	Output height in pixels
`steps`	`10`	Denoising steps
`guidance`	`1.0`	Distilled — CFG is not used
`shift`	`3.0`	Flow-matching timestep shift
`strength`	`1.0`	LLLite control strength (not denoise strength)
`start_percent` / `end_percent`	`0.0` / `1.0`	Fraction of the schedule the control patch is active for

Supported modes: txt2img, img2img (masked inpainting)

Notes and gotchas

strength here is ControlNet conditioning strength, not img2img denoise strength — it scales how hard the LLLite patch holds the source, and the engine also accepts it as control_strength. Lower it to let the masked region drift further from the original.
Quality tags matter. This model responds strongly to booru-style prefixes (masterpiece, best quality, anime illustration, …); without them output drifts toward generic digital painting.
Photographic prompts are off-domain. Asking for a studio photograph yields painterly, illustration-inflected results — use a photo model for that and this one for anime.
≈5.4 GB VRAM resident at 1024². Generation is fast enough (≈6 s) that iterating on prompts is interactive.

Layout

Components ship as separate files: the denoiser, the LLLite inpainting patch under split/model_patches/, the Qwen3-0.6B text encoder, and the VAE. Any loader that accepts explicit per-component paths and can apply a ControlNet- LLLite patch can consume this directly.

Files

File	Size	Role
`split/anima-turbo-v1.0.safetensors`	4.18 GB	denoiser (main weights)
`split/model_patches/anima-lllite-inpainting-v2.safetensors`	65.8 MB	ControlNet-LLLite inpainting patch
`split/text_encoders/qwen_3_06b_base.safetensors`	1.19 GB	Qwen3-0.6B text encoder
`split/vae/qwen_image_vae.safetensors`	254 MB	VAE

Provenance

Upstream base model: Anima Turbo v1.0 (anime-specialised, Qwen-Image family architecture)
This build: redistributed with the inpainting patch, encoder and VAE alongside. Weights are not retrained here.
License: left as unknown in this repo's metadata. Refer to the upstream model's license for redistribution and commercial-use terms.


_{prompt: `masterpiece, best quality, anime illustration of a girl in a school uniform standing on a rooftop at sunset, detailed cel shading, clean linework, dramatic sky` — 1024×1024, 10 steps, guidance 1.0, seed 21}	_{prompt: `masterpiece, best quality, anime illustration, a silver-armored knight with a glowing blue sword in a ruined cathedral, dramatic lighting, detailed` — 1024×1024, 10 steps, guidance 1.0, seed 7}

_{prompt: `masterpiece, best quality, anime background art of a quiet japanese street in summer, blue sky, detailed clouds, vibrant colors, no people` — 1024×1024, 10 steps, guidance 1.0, seed 22}	_{prompt: `masterpiece, best quality, anime illustration, a young woman with long black hair in a white summer dress standing in a flower meadow, blue sky` — 1024×1024, 10 steps, guidance 1.0, seed 21}