Search the full model catalog.

The undistilled 17B-parameter HiDream-I1 text-to-image checkpoint. It is the only one of the three built to run with classifier-free guidance, so the guidance scale and negative prompt both shape the image.

Writes a Markdown report from employee leave records, counting leave by type and by approval status and naming the employees with the highest totals, with English or Turkish as the report language.

Reads a batch of employee pulse surveys and returns JSON for each file with its main themes, requests and a positive and negative sentiment split, plus batch averages, in English or Turkish.

Drafts a culture fit questionnaire for job applicants from a paragraph about your company, optionally drawing on your culture or about page as well.

Scores a candidate's completed culture fit questionnaire against the culture you describe and backs each score with a quote from the candidate's answers.

Qwen Image Edit, the image editing version of Qwen-Image.

Upscales an image up to 4x: FLUX.1 [dev] redraws fine detail while Jasper's upscaler ControlNet holds the layout of the original. Output tops out at 1920 pixels on the longest side.

Qwen's 20B-parameter MMDiT text-to-image model. It draws legible English and Chinese text into the picture, from a single shop sign to a multi-line poster.

Generates a video that morphs one image into another: you set the first and last frames plus a short prompt, and PixVerse v3.5, v4, v4.5 or v5 fills in the motion between them.

Animates one photo with a preset PixVerse effect, either a tiger wrapping its paws around the subject or a zombie makeover of the face, on PixVerse's v4.5 image-to-video model.

Open-weights text-to-image model Black Forest Labs built with Krea, trained for realistic photographic images without the oversaturated textures common in AI output.

Text to speech model from ElevenLabs

Transcribes an audio recording into punctuated plain text with ElevenLabs Scribe v1, which detects the spoken language itself and covers more than 90 languages.

Turns completed exit interview forms into one text report per departing employee, including retention ideas and actions for HR and leadership, in English or Turkish.

Reviews each uploaded CV against a job posting you paste in and says which requirements the CV does not show and how to edit it.

Turns a departing employee's name, department, tenure and role into a full exit interview: a questionnaire to send or a script to read, in English or Turkish.

Text-to-image on FLUX.1 [dev] with one LoRA applied, taken from your private LoRAs or a .safetensors URL, with its strength set by a tag in the prompt.

Generates images from a text prompt with a fixed 4-bit quantized FLUX.1 [dev] and a first-block step cache. There is no model to pick, and a run returns up to eight PNGs.

Seedance 1.0 Pro from ByteDance makes silent 5 or 10 second clips at 480p or 1080p from a prompt, a first frame or a first and last frame pair, and can cut between several shots inside one prompt.

Joins two or more MP4 clips end to end into a single video, in the order you list them, at the frame size of the first clip.