What's new

• Improved understanding of the context around removed objects
• More accurate removal of unwanted objects

• Added the latest, most powerful models
• Added a pricing table
• Improved stability
• Reduced prices for all models (about 20%)
• Free models: gpt-5-mini and deepseek

• Improved image quality and smoother video.
• No censorship

Attention. Activated when there is no image (text only)

• Images come out cleaner and smoother; noticeable "grid" patterns and noise are gone.
• Editing has become more predictable: the model better understands what you ask and does it more accurately.
• Fewer artifacts on faces, skin, and small details.
• More consistent results from run to run.

• API access to the platform's functionality has been added in test mode.
• 50% discount for the duration of the test.
• Get a key and instructions at https://problembo.com/private/api-tokens/tokens

DreamWeaver v2.5

• More realistic images
• Reduced censorship
• Slightly improved overall quality

WildClips v2.1

• Support for lengths up to 20 seconds
• Reduced censorship

AnimeXL v7:

• The overall visual style has been significantly softened — less gloss or "glow".
• Some tags, such as "Mature female", now produce more accurate results.
• Minor improvements for prompts related to furry.
• Better handling of chibi and pixel-art styles.
• The model was further trained on more recent data (characters like Varesa from Genshin now work using only her tag).
• The likelihood of excessive brightness, desaturation, or overly orange/dark results has been greatly reduced.
• Reduced orange/sepia tint on many concepts (including yellowish bodies).
• Artist tags work better.
• Better results for more niche or abstract prompts, not just general ones like "1girl".

VelvetRender v3:

• Significantly increases realism, with crisper anatomy, more stable faces/hands, richer skin and hair details, and more natural lighting.

Main improvements — motion physics and accuracy in responding to prompts. The model confidently handles fights, acrobatics, and other dynamic scenes, eliminating flicker and distortions. Improved ability to interpret complex textual descriptions and abstract concepts.

• Cleaner old scans: automatically removes dust/scratches; remnants can be quickly "healed" with the brush — less manual retouching.
• More natural faces: less "plastic" look; the algorithm auto-adjusts smoothing based on face size.
• Sharpening and noise handled more carefully: more fine details with fewer halos and "jaggies"; previews are closer to the final result.
• Higher-quality upscaling: small details are plausibly redrawn for tiny/soft JPEGs and frames from messengers.
• On "heavy" shots (noise, compression) — fewer blocking/banding artifacts; fabric and skin textures are better preserved.
• Smarter auto settings: more accurate scene recognition and targeted processing — fewer misses in batch processing.