What's new

• Improved speed
• Reduced usage cost
• Improved image generation quality (realism, detail)

• Support for audio. Thanks to a unified process, lip-sync and the rhythm of actions in the frame automatically adjust to the sound. If a character speaks or sings, the footage will match.
• Greatly improved preservation of characters' and objects' appearance when changing frames or angles. This resolves the problem of faces "flickering" in long scenes.
• Understanding of complex prompts improved by ~15%; the model follows the script more accurately.
• Movements are smoother and more physically accurate thanks to better understanding of depth and perspective.

• 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/account/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.