- 🆕 Community SDXL finetune for photorealistic, uncensored character rendering, released 2026.
- 🎯 Specializes in photorealistic character rendering, including explicit content.
- 🔒 Carries Venice's "most uncensored" trait label.
- 🌐 Built on the open-source SDXL lineage of the Lustify series.
- 📚 Lustify checkpoints mix SDXL finetunes refined on curated aesthetics.
- 💬 Earlier Lustify versions parse tag-style and natural-language prompts.
- 🔧 Latest entry in the long-running Lustify checkpoint series.
Community represents the broader ecosystem of independent creators, fine-tuners, and open-source contributors who build and share models outside any single corporate lab. Rather than a formal organization, this category collects specialized models developed by individual…
Explore 4 more models by Community →Lustify v8 is a community-tuned image model built on Stability AI's SDXL architecture and specialized in photorealistic character rendering, including explicit content. It belongs to the long-running Lustify checkpoint series, which earlier versions assembled by mixing an SDXL finetune with checkpoints such as bigASP and Pyro's NSFW, then refining on a curated aesthetic dataset. On Venice it carries the "most uncensored" trait, signaling minimal content filtering.
Within the Lustify family, v8 is the newest release, dated 2026, and the direct successor to Lustify v7, which arrived in early 2025. Both share the same SDXL foundation and the family's focus on realistic, uncensored character imagery. Like earlier versions, the lineage is documented as parsing both danbooru-style tags and natural-language descriptions.
Within Venice's broader catalog, Lustify v8 sits alongside other open image models such as Chroma and the anime-focused Anime (WAI), plus the video model Ovi. As an SDXL-based checkpoint, it inherits that architecture's characteristics and constraints. Independent benchmark figures for this community release are not available from primary or top-evaluator sources, so this description is limited to verifiable, factual details about its lineage and design.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | $ / img | Categories | API |
|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 100.00 | #2 | $0.005 | image,creative,uncensored | openai-images |
| ▲ Apex Ant 0x73b4…e736 | 91.01 | #1 | $0.004 | image,media | openai-images |
| D5V1N2 0xd5e7…7be0 | 33.17 | gated | $0.012 | image,creative,uncensored,router,fallback | openai-images |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = on-chain trust (0-100). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.