Top updates from 2026
November 2026
- fal.ai
speridlabs/idol/max/turbo
Fal's catalog page lists speridlabs/idol/max/turbo, a model that turns one image into a game-ready 3D mesh in about 20 seconds, with optional PBR materials, rigging, and animations. Outputs include GL…
- Featurefal.ai
speridlabs/idol/max
Fal's model page now hosts speridlabs/idol/max, an image-to-3D model that turns one image into a game-ready mesh with optional PBR materials, rigging, and animations. The page lists usage pricing of $…
- Integrationfal.ai
Qwen Image 34.5K-Token Prompts. 12 Languages. Pixel-Perfect Text.
Fal is now offering Qwen Image 3, Alibaba's image generation and editing model, through its serverless API. The model accepts prompts up to 4,500 tokens, renders legible text in 12 languages across mo…
- Launchfal.ai
alibaba/happy-horse/v1.1/text-to-video
fal lists Alibaba's Happy Horse 1.1 text-to-video model, which generates up to 1080p video with native synchronized audio and multilingual lip-sync from a text prompt alone. Output ranges from 3 to 15…
- Integrationfal.ai
microsoft/mai-image-2.7/flash/edit
Fal's platform now hosts microsoft/mai-image-2.7/flash/edit, an endpoint for Microsoft's MAI-Image-2.7 Flash model. It edits images from text instructions and up to two input images, with PNG, JPEG, o…
- fal.ai
microsoft/mai-image-2.7/flash/text-to-image
Fal's platform now hosts Microsoft's MAI-Image-2.7 Flash, described as Microsoft's lower-cost image generation variant, as a text-to-image endpoint. The page lists the model as Partner, Commercial use…
- Launchfal.ai
microsoft/mai-image-2.7/text-to-image
fal's model page lists Microsoft's MAI-Image-2.7, a text-to-image model that generates images from prompts with preset or custom dimensions and PNG, JPEG, or WebP output. The model is marked as partne…
- fal.ai
heygen/avatar-6/turbo/identity-to-video
Fal's platform now lists HeyGen Avatar 6 Turbo, a lower-cost tier of HeyGen's avatar model, as an identity-to-video endpoint. The model generates a talking video of a stock HeyGen avatar speaking eith…
- fal.ai
heygen/avatar-6/turbo/ref-video-to-video
fal lists HeyGen's Avatar 6 Turbo, a lower-cost tier model that animates an animated or illustrated character from a reference video into a talking video lip-synced to supplied speech audio. Videos of…
- Integrationfal.ai
heygen/avatar-6/turbo/image-to-video
Fal's model catalog now lists HeyGen Avatar 6 Turbo, the lower-cost tier of HeyGen's image-to-video model, as a hosted endpoint. The model takes a photo of a person and a supplied speech audio track a…
- fal.ai
microsoft/mai-image-2.7/edit
fal's platform now lists microsoft/mai-image-2.7/edit, an endpoint that edits images from text instructions and up to two input images, with preset or custom dimensions and PNG, JPEG, or WebP output. …
- fal.ai
kling/v4/image-to-image
Fal's catalog page lists a kling/v4/image-to-image endpoint, priced at $0.063 per unit with 4K and 16:9 options. The page states that provider integration is still pending and the endpoint currently r…
- Integrationfal.ai
kling/v4/text-to-image
Fal's catalog now lists a kling/v4/text-to-image endpoint priced at $0.063 per unit, with 4K output and 16:9 aspect ratio options. The page states that provider integration is still pending and the en…
- fal.ai
speridlabs/iris-z/small/text-to-rgbd
Fal now hosts speridlabs' Iris-Z Small, a lighter FLUX.2-based model that generates an RGB image, a colorized depth map and a float32 log-depth array from a text prompt, at roughly a third of the gene…
- fal.ai
speridlabs/iris-z/small/text-to-image
Fal's platform now lists speridlabs' Iris-Z Small, a lighter variant of a FLUX.2-based joint RGB and depth model, which the listing says generates images at roughly a third of Iris-Z's generation time…
- Integrationfal.ai
speridlabs/iris-z/depth-to-image
Fal's model catalog now includes speridlabs/iris-z/depth-to-image, a depth-guided image generation model built on FLUX.2 that jointly handles RGB and depth. It accepts depth, disparity, or colorized d…
- Launchfal.ai
speridlabs/iris-z/text-to-rgbd
Fal's platform now hosts speridlabs/iris-z/text-to-rgbd, a FLUX.2-based model that generates an RGB image, a colorized depth map and a float32 log-depth array from a text prompt. It supports preset or…
- fal.ai
speridlabs/iris-z/text-to-image
Fal's platform now hosts speridlabs/iris-z, a text-to-image model described as a FLUX.2-based joint RGB and depth model. It supports preset or custom sizes up to 1.31 MP with both sides in multiples o…
- fal.ai
speridlabs/iris-z
Fal's model catalog now hosts speridlabs/iris-z, a FLUX.2-based model that estimates relative depth from a single image, returning a colorized depth map and a float32 log-depth array at input resoluti…
- fal.ai
speridlabs/iris-z/small/depth-to-image
Fal's model catalog now hosts speridlabs' Iris-Z Small, a lighter FLUX.2-based joint RGB and depth model that generates images following a depth, disparity, or colorized depth map. It takes about a th…
Top 20 shown. Click a month above for the full archive of Fal.
Track Fal on autopilot
- · Weekly AI brief: narrative summary of what shipped, every Monday 9 AM
- · Email or Slack alerts, or chat with the archive in your dashboard
- · Add Fal + up to 2 more competitors free, no credit card